Loading…

Log in to bookmark your favorites and sync them to your phone or calendar.

Thursday, August 22
 

8:00am

Registration, Networking, & Coffee
Thursday August 22, 2019 8:00am - 9:00am

9:00am

Kickoff: MinneAnalytics & Questrom School of Business
Thursday August 22, 2019 9:00am - 9:15am

9:15am

Break
Thursday August 22, 2019 9:15am - 9:30am

9:30am

Senior Leadership Panel: Future Directions of Analytics
This panel includes senior leaders from across industry, academia & government to discuss challenges they are tackling, needs they anticipate and goals they will achieve.

Moderators
avatar for Bonnie Holub, PhD

Bonnie Holub, PhD

Data Science Practice Lead, Teradata
Bonnie has a PhD in Artificial Intelligence and specializes in correlating disparate sets of Big Data for actionable results.

Speakers
avatar for Candace Sleeman, MS, PhD

Candace Sleeman, MS, PhD

STEM Technical Program Facilitator, Southern New Hampshire University
Dr. Sleeman specializes in technical research team leadership, big data analytics and applied data science. She holds a PhD in Mathematics from Drexel University, and is a member of the Board of Trustees for the NorthEast Regional Computing Program.
avatar for David Gardiner, PhD

David Gardiner, PhD

Principal Data Scientist, Digi-Key Electronics
David has been doing data science since before the term existed, and AI since before it was cool. He currently works for Digi-Key Electronics, a leading electronic component distributor, helping the company better understand and optimize its business. Prior to that David was a founder/co-founder... Read More →
avatar for George Bier

George Bier

Technology Distinguished Engineer and Senior Director of Architecture & Engineering, Optum
George is an Optum Technology Distinguished Engineer supporting OptumHealth initiatives with a focus on technology and platform selection, architectural designs, agile delivery, EMR/EHR integration with an emphasis on evolving FHIR and SMART on FHIR standards, and the adoption of... Read More →


Thursday August 22, 2019 9:30am - 10:15am
Auditorium 595 Commonwealth Avenue, Boston, MA 02215, USA

9:30am

Startup Showcase
The startup showcase session features pitches from up-and-coming startups doing something cool with data, analytics, or AI. Each pitch is followed by a brief Q&A. We welcome startups based in the Boston area and beyond. To submit a startup, fill out the form here or contact Graeme Thickins (graeme@minneanalytics.org).


Thursday August 22, 2019 9:30am - 10:15am
Room 322 595 Commonwealth Avenue, Boston, MA 02215, USA

9:30am

Creating value with AI: Building and managing data science teams for maximum business impact
We live in an era in which data is unquestionably the new currency. All sectors of the industry and disciplines in academia are searching for creative ideas to leverage the ever expanding information space. As is with any new trend, we see some justified skepticism as well as a lot of opportunistic hype around AI. There is no generic rule for hitting the right level of investment into AI and how to structure the business operations in tandem with Machine Learning/Analytics/Informatics efforts. We already see a small number of companies taking minimal risk with smart choices and thereby making headway in revolutionizing how they wield information. Creating value with AI is often not only related to creating fancier ML/DL algorithms. A holistic overhaul to create a synergistic ecosystem has proven to be critical for success. I will talk about what I’ve learned over two decades from successes and failures about how to execute relevant strategies so we can more effectively create value with AI.

Speakers
avatar for Bülent Kiziltan, PhD

Bülent Kiziltan, PhD

Head of Data Science & Analytics, Stealth Mode Elite Consultancy Startup
Dr. Bülent Kiziltan is an accomplished scientist and an AI executive who uses artificial intelligence to create value in many business verticals. He has worked at Harvard, NASA and MIT in close collaboration with pioneers of their respective fields.


Thursday August 22, 2019 9:30am - 10:15am
Rooms 426 / 428 / 430 595 Commonwealth Avenue, Boston, MA 02215, USA

9:30am

Predicting Leaders (and Followers) from online interactions
What if we could take video (and text, chat, etc) and use what we know about human signals and social physics to *augment* our online interactions and start to make them better and maybe even more informative than in-person meetings? What could we learn? How might that help us be more effective in remote teams? 

Speakers
avatar for Beth Porter, MA

Beth Porter, MA

CEO, Riff Learning Inc
Beth’s philosophy is that people learn best from each other, and learning fosters both personal growth and organizational innovation and change. She teaches IT Strategies at Boston University and in the Media Ventures team at the MIT Media Lab.


Thursday August 22, 2019 9:30am - 10:15am
Room 404 595 Commonwealth Avenue, Boston, MA 02215, USA

9:30am

Bayesed and Confused: Assessing the Ethical Implications of AI models
AI models that generate predictions have ethical implications when deployed in the real world. This has led to efforts to combat algorithmic bias and fairness by analyzing the confusion matrix to understand the implications of model misclassification. This presentation showcases a free, publicly available app that helps data scientists assess algorithmic bias. The app is powered by a probabilistic Bayesian model that supports the interpretation of the confusion matrix. The presentation focuses on the use case of predicting rare adverse events in the hospital setting.

Speakers
avatar for Alex Bohl, PhD

Alex Bohl, PhD

Director of Data Science, Mathematica
Dr. Bohl applies machine learning algorithms to healthcare claims to risk-adjust quality measures and design value-based payment programs. He directs Mathematica’s data science staff and leads business development efforts.


Thursday August 22, 2019 9:30am - 10:15am
Room 408 595 Commonwealth Avenue, Boston, MA 02215, USA

9:30am

Did a Machine Write My Talk?
For years, news agencies have been automatically generating formulaic news articles.   Now, however, deep learning architectures enable computers to summarize highly technical or specialized texts at a high level.   What is the state of the art, where is it going and should we be concerned? 

Speakers
avatar for Brian Ulicny, PhD

Brian Ulicny, PhD

VP, Americas, Thomson Reuters
Dr. Brian Ulicny is VP, Thomson Reuters Labs - Americas. The Labs partner with customers, internal teams, start-ups and academics, to create new data-driven innovations utilizing Thomson Reuters’ vast, curated data sets across many disciplines.


Thursday August 22, 2019 9:30am - 10:15am
Room 306 595 Commonwealth Avenue, Boston, MA 02215, USA

9:30am

Reducing ML prediction uncertainty with systems-thinking in high-stakes events
This presentation will cover our current research on an unsolved problem - how to apply systems thinking to reduce prediction uncertainty from machine learning models applied to high-consequence outcomes. The specific focus of this presentation will be on machine damage progression to catastrophic failure. Every wrong prediction about the health of machine can either lead to a machine failure costing millions of dollars or causing an operator to stop a machine thinking it is damaged when it is not - both scenarios are bad. This presentation will focus on a specific kind of large machine - wind turbines and discuss our current challenges dealing with prediction uncertainty and related adverse business outcomes from trying to do this for thousands of such turbines.

The presentation will show our attempts at building a system to represent the entire system of factors which cause large machines to have damage progression and eventual failure. The presenter will try to illustrate why this is hard to build and deploy as features in machine learning models and discuss our various attempts at it. Uncertainty is a less-talked-about topic in machine learning but it is critical when these algorithms directly impact the physical world. In terms of technical content, this will touch upon topics such as signal-to-noise ratio in stochastic time-series, difference in spatial and temporal resolution of various data sources, uncertainty quantification and propagation framework (e.g. Kalman Filters) for variety of machine learning models and last but not the least, adverse impact of benign human habits - we will cover ideas that we have tried to deploy to quantify and detect these issues.

The overall goal of this presentation is to (a) describe a hard, unsolved problem of significant consequence not only economically but also on one of the greatest challenges facing us - climate change and, (b) simulate a discussion and ideas-exchange in the wider community. 

Speakers
avatar for Vijayant Kumar, PhD

Vijayant Kumar, PhD

Vice President - Data Science & Engineering, Sentient Science
Vijayant Kimar leads the predictive analytics team at Sentient Science and is focused on using data science and physics-driven modeling to provide diagnostics and prognostics to allow optimized predictive maintenance of large machinery. 


Thursday August 22, 2019 9:30am - 10:15am
Room 211 595 Commonwealth Avenue, Boston, MA 02215, USA

9:30am

Advancing Cancer Research with Deep Learning Image Analysis
Histopathological images are the gold standard tool for cancer diagnosis, whose interpretation requires manual inspection by expert pathologists. This process is time-consuming for the patients and subject to human error. Recent advances in deep learning models, particularly convolutional neural networks, combined with big databases of patient histopathology images will pave the path for cancer researchers to create more accurate guiding tools for pathologists. In this talk, I will review the latest advances of big data in healthcare analytics and focus on deep learning applications in cancer research. Targeted at a general audience, I will provide a high-level overview of technical concepts in deep learning image analysis, and describe a typical cloud-based workflow for tackling such big data problems. I will conclude my talk by sharing some of our most recent results based on a wide range of cancer types. 

Speakers
avatar for Mohammad Soltanieh-ha, PhD

Mohammad Soltanieh-ha, PhD

Clinical Assistant Professor, Boston University - Questrom
Mohammad is a faculty at Boston University, Questrom School of Business, where he teaches data analytics and big data to master's students. Mohammad's current research area involves deep learning and its applications in cancer research.



Thursday August 22, 2019 9:30am - 10:15am
Room 406 595 Commonwealth Avenue, Boston, MA 02215, USA

10:15am

Break
Thursday August 22, 2019 10:15am - 10:30am

10:30am

You Built It, But They Didn't Come: How Human-Centered Design Increases the Value of Decision Support Tools
In 2019, Gartner predicted 80%+ of analytics insights won’t deliver outcomes through 2022—despite ongoing and sizable investments in technology and data. Executives are worried about having an AI strategy. Data scientists worry about getting their models to be as accurate as possible. IOT teams stay busy juggling telemetry, alerts, and APIs. Report developers do their best to visualize the data, and engineers try to glue it all together and ship it. However, if business value is dependent on specific users engaging successfully with a decision support application or data product, then teams must design these solutions around the people using them—not the data or technology. Human-centered design provides a process to help teams discover, define, and fall in love with customer problems and needs so that solutions encourage meaningful engagement and outcomes, and the business realizes value from its investment in analytics. In this mini-workshop, Brian will share some common causes of low engagement with data products, introduce the design process, and teach attendees to apply one design technique in a small group setting. 

Speakers
avatar for Brian O'Neill

Brian O'Neill

Founder and Principal, Designing for Analytics
Brian helps enterprise companies turn data into indispensable data products and services. He is a product designer and host of the podcast, "Experiencing Data."


Thursday August 22, 2019 10:30am - 11:00am
Room 404 595 Commonwealth Avenue, Boston, MA 02215, USA

10:30am

Establishing a Health Information Exchange at a Medical Device Company
An overview of why an HIE is key to enabling a Medical Device company to leverage its device data in the Health Care industry. By combining clinical, socioeconomic, and medical device data (among others) we can more precisely measure therapy health outcomes and also fine-tune device settings to fit the patient profile. Also, there is a need to make medical device data interoperable so that it can easily flow into Provider and Payer ecosystems.

Speakers
avatar for Stasha Ler

Stasha Ler

Director Digital Health, Medtronic
Stasha leads the Medtronic Digital Health Foundry team.  He’s responsible for enabling digital health data integration and analytics platform for emerging business models such as Value Based Healthcare.


Thursday August 22, 2019 10:30am - 11:00am
Room 408 595 Commonwealth Avenue, Boston, MA 02215, USA

10:30am

A Review of Data Sources used in Sports Analytics
Sports Analytics is a growing industry, and many practitioners have asked me about how to get a start in answering their own questions.  This talk will review and discuss the publicly available datasets for baseball, basketball, American Football, hockey and soccer. 

Speakers
avatar for Andy Andres, PhD

Andy Andres, PhD

Senior Lecturer, Boston Univeristy
Andy Andres created and taught the still popular Sports Analytics course on edx.org (over 50,000 registered students), "Sabermetrics 101: An Introduction to Baseball Analytics" 


Thursday August 22, 2019 10:30am - 11:00am
Room 306 595 Commonwealth Avenue, Boston, MA 02215, USA

10:30am

Acceleration Solutions for Big Data & HPC
Intel FPGAs are being utilized by large CSPs, University and Research institutes to accelerate many compute intensive application.  Intel has made the FPGA technology available in standard high volume servers from the leading system vendors.  These systems, coupled with solution from ISVs or Intel C level software development tools, are being used for advanced research in genomics, database analytics, AI, molecular modeling and more.

Speakers
avatar for Nick Finamore, BSEE

Nick Finamore, BSEE

Director, World Wide Data Center - Programmable Solutions Group, Intel


Thursday August 22, 2019 10:30am - 11:00am
Room 322 595 Commonwealth Avenue, Boston, MA 02215, USA

10:30am

Data Science for a Home Insurance Product
Plymouth Rock Home Group (BunkerHill insurance) started a new product in 2016 with the best customer service experience in mind.  When customers come shopping for insurance needs, instead of the traditional lengthy quoting process, we offer them fast quoting by pre-rate all properties.  As the core of the business strategies, Data Science is playing a vital role for the product. Our home product is heavily digitalized, leaning on multiple data and advanced predictive analytics.  We apply Data Science on our multiple data assets to identify customers who could be good targets for our product and reach out to them proactively. In this presentation, we will review how our Data Science team is supporting business strategies around marketing, underwriting, claims, and renewals.

Speakers
avatar for Shawn Jin

Shawn Jin

Head of Analytics, Bunker Hill Insurance
Shawn Jin leads Data Science team to support rapid growth of the home product in Plymouth Rock Home Group (Bunker Hill Insurance) through advanced analytics.  Previously Shawn focused on analytics in AIG, McKinsey, Targetbase, Merkle and CapitalOne.


Thursday August 22, 2019 10:30am - 11:00am
Room 211 595 Commonwealth Avenue, Boston, MA 02215, USA

10:30am

Deep learning image recognition and classification models for fashion items
Large scale image recognition and classification is an interesting and challenging problem. This case study uses fashion-MNIST dataset that involves 60000 training images and 10000 testing images. Several popular deep learning models are explored in this study to arrive at a suitable model with high accuracy. Although convolutional neural networks have emerged as a gold-standard for image recognition and classification problems due to speed and accuracy advantages, arriving at an optimal model and making several choices at the time of specifying model architecture, is still a challenging task. This case study provides the best practices and interesting insights. 

Speakers
avatar for Bharatendra Rai

Bharatendra Rai

Professor, UMass Dartmouth
Bharatendra Rai, Ph.D. is Professor of Business Analytics in the Charlton College of Business at UMass Dartmouth. His research interests include machine learning & deep learning applications.  


Thursday August 22, 2019 10:30am - 11:00am
Room 406 595 Commonwealth Avenue, Boston, MA 02215, USA

10:30am

What do you do with limited data?
While businesses are utilizing big data in predictive analytics, what can you do when data is limited in quantity or quality? Come to this session to learn best practices in generating insights from insurance companies who have implemented analytics solutions in sales, marketing, operations, claims, finance. You are encouraged to submit questions ahead of time.

Speakers
avatar for Nirav Dagli

Nirav Dagli

President and CEO, Spinnaker Analytics LLC
Nirav is the founder and CEO of Spinnaker Analytics. He was a partner at Oliver Wyman. Worked at MITRE Corporation. He serves on the boards of financial services and energy companies and as Chairman of the Boston Children's Museum board.
avatar for Manish Gupta

Manish Gupta

Data Scientist, Spinnaker Analytics LLC


Thursday August 22, 2019 10:30am - 11:00am
Auditorium 595 Commonwealth Avenue, Boston, MA 02215, USA

10:30am

A Bayesian Look at Clinical Risk Prediction
Building reliable predictive and prognostic models that leverage the growing scale of medical data and clinical records can make tremendous impact to the healthcare industry. Traditional survival analysis originated from clinical research focuses on identifying variates and factors that affect the hazard function; time series modelling approaches emphasize predicting future values based on previous observations; machine learning models are often formulated as mapping between large feature spaces to binary outcomes. However, all of these methods have their unique limitations and there are still much more to explore in the context of treating clinical survival analysis with machine learning models. In this talk, we will present our recent work on a new Bayesian framework that uniquely connects machine learning tasks (classification/regression) with event time analysis to provide risk prediction capabilities. We validate and demonstrate the utility of this approach with simulation data where the ground truths are known. We will then show a specific use case of this approach to perform risk prediction with real medical datasets. We will also discuss how this model can be implemented into clinical solutions.

Speakers
avatar for Kang Liu

Kang Liu

Applied Data Scientist, Wolters Kluwer Health
Dr. Kang Liu graduated with his Ph.D. from Boston University in 2013 and now works as an Applied Data scientist at Wolters Kluwer Health where he builds machine learning models for the early prediction of hospital-acquired infection.


Thursday August 22, 2019 10:30am - 11:00am
Rooms 426 / 428 / 430 595 Commonwealth Avenue, Boston, MA 02215, USA

11:00am

Break
Thursday August 22, 2019 11:00am - 11:15am

11:15am

The Ethics Of Analytics
As more and more data is being collected, concerns are constantly being raised about what data is appropriate to collect and how (or if) it should be analyzed. There are many ethical, privacy, and legal issues to consider, and no clear standards exist in many cases as to what is fair and what is foul. This means that organizations must consider their own principles and risk tolerance in order to implement the right policies.

This talk explores a range of ethical, privacy, and legal issues that surround analytics today, framing the big questions to consider and detailing some of the trade-offs and ambiguities that must be addressed to answer them. 

Speakers
avatar for Bill Franks

Bill Franks

Chief Analytics Officer, International Institute for Analytics
Internationally recognized analytics, data science, AI, & big data thought leader, speaker, executive, and author


Thursday August 22, 2019 11:15am - 12:00pm
Rooms 426 / 428 / 430 595 Commonwealth Avenue, Boston, MA 02215, USA

11:15am

Applying AI to healthcare
The technical, regulatory, economic, clinical, and business cases, opportunities, and obstacles in applying AI and Blockchain to healthcare and life science problems and solutions.

Speakers
avatar for David Crais CMPE PMP

David Crais CMPE PMP

Board Member, CMG Carealytics


Thursday August 22, 2019 11:15am - 12:00pm
Room 322 595 Commonwealth Avenue, Boston, MA 02215, USA

11:15am

From Artisanal Analytics to AI
There have been four different approaches for applying analytics to business over the last half century. Some organizations still practice Analytics 1.0 (the artisanal era), while others are actively pursuing Analytics 4.0 (the AI era). Each era requires different management of both analytics and the underlying data. In this presentation Tom Davenport will describe the attributes of each era, the drivers of change, and the valuable lessons that each era provides. He will focus on the state of enterprise AI and how firms can move from traditional analytics to the power and capability that AI methods hold.

Speakers
avatar for Tom Davenport, PhD

Tom Davenport, PhD

Distinguished Professor, Research Fellow, Senior Advisor, Babson College / MIT / Deloitte Analytics
Tom Davenport is a Distinguished Professor of IT and Management at Babson College, Fellow of the MIT Initiative on the Digital Economy, Senior Advisor to Deloitte's Analytics and Cognitive practice, and co-founder of the International Institute for Analytics.


Thursday August 22, 2019 11:15am - 12:00pm
Auditorium 595 Commonwealth Avenue, Boston, MA 02215, USA

11:15am

Multilingual NLP for clinical text: impacting healthcare with big data, globally
At Droice, we leverage massive repositories of clinical text to build deep learning/NLP solutions to help clinicians make better decisions for individual patients. With the widespread adoption of electronic medical records (EMRs) and recent advances in machine learning, natural language processing has come to the forefront in clinical AI. Despite the challenges of working with unstructured text, doctors’ notes and other clinical text contains some of the richest information about a patient. However, building systems that can work with clinical text in languages other than English remains a challenge to this day. In this talk, we will present several real-world use cases of NLP-powered solutions in several languages. 

Speakers
avatar for Mayur Saxena, PhD

Mayur Saxena, PhD

CEO, Droice Labs
Mayur serves as the CEO of Droice Labs, an AI/Big Data healthcare company based in NY. Mayur earlier co-founded Ardent Cell Technologies, a cell therapeutics company in the diabetes space, where the technology is undergoing human clinical trials.
avatar for Tasha Nagamine, MS, PhD

Tasha Nagamine, MS, PhD

Chief AI Officer, Droice Labs


Thursday August 22, 2019 11:15am - 12:00pm
Room 306 595 Commonwealth Avenue, Boston, MA 02215, USA

11:15am

Regularization and Functional Methods to Predict Nutrients
Mineral nutrients play an important role in the biochemistry of grapevine and its growth. Grapevines are known to store significant quantities of certain nutrients to overcome their short-term scarcities in the soil. Hence viticulturists have developed a lot of interest in studying the relationship between the biochemistry of the leaf/petiole and its spectral reflectance to understand the fruit ripening rate, water status, nutrient levels, and disease.  

The dataset obtained by measuring the spectral reflectance, defined as the ratio of backscattered radiance from a surface and the incident radiance on that surface, directly over the leaves during the bloom period of growth data in the wavelength region of 330 – 2500 nanometers. This will yield a high dimensional reflectance data with an ill-conditioned covariance matrix. Four regularization and one functional regression method is compared to improve the estimation accuracy and enhance the model interpretability by selecting continuous, unbiased, sparse and useful variables (wavelengths).  

Speakers
avatar for Uday Jha, MS

Uday Jha, MS

Full-Time Lecturer, University of Massachusetts, Dartmouth
Uday Jha teaches Business Statistics and Business Analytics at University of Massachusetts, Dartmouth.


Thursday August 22, 2019 11:15am - 12:00pm
Room 408 595 Commonwealth Avenue, Boston, MA 02215, USA

11:15am

Applying Artificial Intelligence to Python Coding Courses
A pilot was run at Southern New Hampshire University testing the efficacy of personalized feedback in sections of an online Introduction to Python course.  We saw a statistically significant increase in student submission and success rates, and are continuing the pilot as we continue to improve the course. 

Speakers
avatar for Candace Sleeman, MS, PhD

Candace Sleeman, MS, PhD

STEM Technical Program Facilitator, Southern New Hampshire University
Dr. Sleeman specializes in technical research team leadership, big data analytics and applied data science. She holds a PhD in Mathematics from Drexel University, and is a member of the Board of Trustees for the NorthEast Regional Computing Program.


Thursday August 22, 2019 11:15am - 12:00pm
Room 406 595 Commonwealth Avenue, Boston, MA 02215, USA

11:15am

Future of HPC & AI Convergence
The talk covers the convergence of HPC & AI, then provides examples of AI workloads in Imaging, High Content Screening, de novo Chemical Structure Generation, and Genomics.

Speakers
avatar for Michael McManus, PhD

Michael McManus, PhD

Principal Engineer, Intel
Dr. McManus has over 30 years of scientific software/hardware and business experience. 


Thursday August 22, 2019 11:15am - 12:00pm
Room 211 595 Commonwealth Avenue, Boston, MA 02215, USA

11:15am

Rapid Data Science
Most companies today require fast, traceable, and actionable answers to their data questions. This talk will present the structure of the data science process along with cutting edge developments in computing and data science technology (DST) with direct applications to real world problems (with a lot of pictures!). Everything from modeling to team building will be discussed, with clear business applications. 

Speakers
avatar for Erez Kaminski

Erez Kaminski

Leaders Global Operations Fellow, MIT
Erez has spent his career helping companies solve problems using data science. He is currently a graduate student in computer science and business at MIT. Previously, he worked in data science at Amgen Inc. and as a technologist at Wolfram Research. 


Thursday August 22, 2019 11:15am - 12:00pm
Room 404 595 Commonwealth Avenue, Boston, MA 02215, USA

12:00pm

Lunch
Thursday August 22, 2019 12:00pm - 1:00pm

1:00pm

Boston Data Science Community: An Open Discussion
Join the conference organizers for an open discussion about the data science community in Boston.

Thursday August 22, 2019 1:00pm - 1:45pm
Room 211 595 Commonwealth Avenue, Boston, MA 02215, USA

1:00pm

Health and Healthcare Data Visualization - See how you're doing
Health and healthcare organizations are swimming in data but few have the skills to show and see the story in their data using the best practices of data visualization. This presentation raises awareness about the research that inform these best practice and stories from the front of groups who are embracing them and re-imagining how they display their data and information. These groups include the NYC Dept of Health & Mental Hygiene, The Centers for Medicare and Medicaid (CMS), and leading medical centers and providers across the country. 

Speakers
avatar for Katherine Rowell

Katherine Rowell

Co-Founder & Principal, Health Data Viz
Katherine Rowell is a health, healthcare, and data visualization expert. She is Co-founder and Principal of HealthDataViz, a Boston firm that specializes in helping healthcare organizations organize, design and present visual displays of data to inform their decisions and stimulate... Read More →


Thursday August 22, 2019 1:00pm - 1:45pm
Auditorium 595 Commonwealth Avenue, Boston, MA 02215, USA

1:00pm

Machine Learning in Practice: Anomaly Detection for Army ERP Data
Machine learning and artificial intelligence (AI) are two areas that show tremendous potential for a wide variety of use cases, helping to augment, inform, and supplement human processes.  In practice, most companies have fallen short in actually implementing these strategies, since most organizations are still trying to make sense of their data.

However, this doesn’t mean machine learning solutions should be scrapped until your organization’s data is flawless. Instead, machine learning and AI can be used to better understand operational data, uncover the root cause of data issues, resolve existing data errors, and prevent future errors by addressing the source of each anomaly.

In this session, we’ll review a machine learning case study for the Department of Defense. During this project, the team set out to evaluate the potential of machine learning and AI in improving operational data quality and thereby increasing Army readiness. The team launched a pilot analysis and proof of principle to demonstrate how machine learning and AI algorithms, protocols, and methodologies can address known flaws in existing datasets and capitalize on pattern recognition to produce data cleansing models. A progression of analysis and machine learning approaches were leveraged to better understand problematic datasets within the Army’s ERP environment, identify and classify anomalies, and ultimately provide a path to resolution.

During this session, we’ll highlight the machine learning technologies and approaches, both supervised and unsupervised, that were used to best uncover and resolve data anomalies. We’ll also review the anticipated next steps for the Army with AI that are designed to prevent future data quality issues and actively monitor their ERP environment.

Speakers
avatar for Tanya Cashorali

Tanya Cashorali

Founder, TCB Analytics
Tanya Cashorali is the founder of TCB Analytics, a data and analytics consultancy. She leads a world-wide community network of 400 data enthusiasts, has helped universities launch data science programs, and is a frequent speaker at tech conferences. 


Thursday August 22, 2019 1:00pm - 1:45pm
Room 404 595 Commonwealth Avenue, Boston, MA 02215, USA

1:00pm

Implementing Data Science - SESSION CANCELED
Speakers
avatar for Jamie Warner

Jamie Warner

Director, Advanced Analytics and Data Science, Lincoln Financial Group


Thursday August 22, 2019 1:00pm - 1:45pm
Room 211 595 Commonwealth Avenue, Boston, MA 02215, USA

1:00pm

Technical drivers of cloud centralization and megacorporate domination
Find out why data is becoming more centralized and how analytics drive the collection of data.

Speakers
avatar for Andrew Oram

Andrew Oram

Editor, O'Reilly Media
Andy Oram brought to publication O'Reilly's Linux series, the ground-breaking book Peer-to-Peer, and the best-seller Beautiful Code. Andy has also authored many reports on technical topics such as data lakes and open source software.


Thursday August 22, 2019 1:00pm - 1:45pm
Room 306 595 Commonwealth Avenue, Boston, MA 02215, USA

1:00pm

Shapelets via Procrustes Tangent Distance matching
Shapelets are compact abstracted feature descriptors mined from time series. They have been used for qualitative and high school cross-correlation of series, and for classifying phenomena and behaviors in evidence within series, particularly if the record is of human activity. Traditionally these are devised by hand, with domain knowledge, and then procedures like variable selection used to winnow and tune them. Automatic discovery has been explored, using techniques like Dynamic Time Warping, but these can be expensive. Matching using Procrustes Tangent Distance (Dryden, Mardia, Kent, Rohlf, 1993, 1994, 1999) is introduced here, and libraries of features are built by auto-correlating series using this operator. Libraries from different series can then be compared to discern similarities and generalize. Applications to electricity consumption series and to hydrological stream flow are used to illustrate.

Speakers
avatar for Jan Galkowski

Jan Galkowski

Statistician, Quantitative Engineer, Westwood Statistical Studios
Professionally, I do Internet sociology at a major Internet company in the Kendall Square area. I also volunteer statistical skills to local governments and non-profits, helping to promote sustainability and assess spatiotemporal risks. My technical interests are computational statistical... Read More →



Thursday August 22, 2019 1:00pm - 1:45pm
Room 408 595 Commonwealth Avenue, Boston, MA 02215, USA

1:00pm

Style-Aware Product Recommendation using Deep Ranking
Interior design and home decoration heavily rely on guesswork. Customer's stylistic preference is an important factor in deciding which product to buy. Although there exist different types of styles defined by designers, labeling a scene with a style is a highly subjective task. Furthermore, customers often cannot verbalize their style preference, but can identify their preferences by looking at images. Thus, it is crucial to show products in a room context that are tailored to a customer's taste. We collect a dataset of room images labeled by interior design experts and encounter high inter-expert variability in style labels. We overcome this limitation by generating comparisons, each indicating the relative order between a pair of images. We present a deep learning based image retrieval framework to predict style from the generated comparisons. Given a seed room image, our framework predicts the style spectrum and provides a ranked list of stylistically similar room images from the catalog. Our architecture is inspired by siamese networks and extends the Bradley-Terry model to learn from comparisons. Extensive experiments show that our framework does not only accurately estimate room style, but also learns distinctive visual features reflecting style.

Speakers
avatar for Esra Cansizoglu

Esra Cansizoglu

Lead Machine Learning Engineer, Wayfair
Esra is a machine learning engineer at Wayfair developing methods to provide an algorithmic understanding to room design. She holds an MS in Computer Science from Boston University and a PhD in Electrical Engineering from Northeastern University.


Thursday August 22, 2019 1:00pm - 1:45pm
Room 406 595 Commonwealth Avenue, Boston, MA 02215, USA

1:00pm

Anomaly Detection Introduction
If you have a data pipeline, you will have data anomalies in it sooner orlater.  If you don't notice them, at best you'll get degraded model performance, and at worst you'll miss important changes in your business environment.

In this talk you will learn how to apply regression and dimensionality reduction techniques to the anomaly detection problem. We'll also discuss investigation and diagnosis of the potential anomaly once it has been detected. Don't be intimidated by all the papers about novel anomaly detection algorithms - idiosyncratic algorithms are not equired, and in fact can sometimes produce warnings that are harder to diagnose than using simpler techniques.

To benefit from this talk, attendees should have a conceptual familiarity with at least one of linear regression, principal component analysis, and chi-squared tests. 

Speakers
avatar for Terran Melconian, SM

Terran Melconian, SM

Data Science Trainer and Consultant, Independent
Terran has worked in all aspects of the data lifecycle at companies like TripAdvisor and Google: software, ranking, warehousing, and modeling. He is now a data science educator and consultant, sharing his knowledge with developing professionals.


Thursday August 22, 2019 1:00pm - 1:45pm
Rooms 426 / 428 / 430 595 Commonwealth Avenue, Boston, MA 02215, USA

1:45pm

Break
Thursday August 22, 2019 1:45pm - 2:00pm

2:00pm

Navigating a Data Driven Career
In 2017 I made the decision to pursue my passion for analytics and to move out of my traditional finance role. Navigating the wealth of areas and emphasis that come along with analytics and data science, I found my desired destination. There were learnings and resources that proved very valuable. I'm looking to pass on this field operative view and experience for those looking to navigate the same space. 

Speakers
avatar for David Barton

David Barton

Associate Director of Business Analytics, Optum / Post Acute
David Barton has 11+ years with Optum/UHG in FP&A, with previous work with Target and Wells Fargo in analytics, portfolio management, and strategic planning. David recently made the career transition from Finance into Analytics with the help of communities like MinneAnalytics.


Thursday August 22, 2019 2:00pm - 2:45pm
Room 404 595 Commonwealth Avenue, Boston, MA 02215, USA

2:00pm

AI in Healthcare
Benefits, challenges and impact of AI and Cybersecurity on medicine.

Speakers
avatar for Vinit Nijhawan

Vinit Nijhawan

Lecturer, Boston University
Vinit Nijhawan is an Entrepreneur, Academic, and Board Member with a track record of success, including 4 startups in 20 years.


Thursday August 22, 2019 2:00pm - 2:45pm
Auditorium 595 Commonwealth Avenue, Boston, MA 02215, USA

2:00pm

Minding the Gap: Understanding and Mitigating Bias in AI
The presentation will highlight the ways inherent bias can exist in AI programs and how market researchers can identify and navigate these potential land mines. 

Speakers
avatar for Jackie Anderson

Jackie Anderson

Growth Strategist, ScaleHouse
Jackie helps businesses identify strengths, mitigate weaknesses,& accelerate growth. Previously, Jackie served as Chief Client Officer at Simmons Research and held various roles at Forrester & J.D. Power & Assoc. She is currently the head of WIRe Boston. 


Thursday August 22, 2019 2:00pm - 2:45pm
Rooms 426 / 428 / 430 595 Commonwealth Avenue, Boston, MA 02215, USA

2:00pm

Accelerate delivery of ML-based products
This talk will examine a case study in using open source tools (ioModel) and a grounding in statistics to rapidly develop and deliver to market an instrument capable of forecasting the onset of dementia 1-10 years before a doctor could diagnose it. This same disciplined method and approach can and should be leveraged in the commercial industry to rapidly accelerate the delivery of ML-based products and features while reducing cost and the rate of failure of data science initiatives.  

Speakers
avatar for Matt Hogan

Matt Hogan

Founder, Twin Tech Labs
Matt is a passionate technologist and futurist and believes that we stand to build the greatest products by studying the intersection of people and technology, both when products are being built and in how they are being used. 


Thursday August 22, 2019 2:00pm - 2:45pm
Room 406 595 Commonwealth Avenue, Boston, MA 02215, USA

2:00pm

Enabling Your Data Science Team with Modern Data Engineering
This session will make the case for how an effective and forward-thinking data engineering team can become a key partner with a data science team. James will discuss how data engineering teams should consider their data science peers when building data infrastructure, and how data science teams can best communicate with data engineers.

Speakers
avatar for James Densmore, MBA

James Densmore, MBA

Founder and Principal Consultant, Data Liftoff
James is the Founder and Principal Consultant at Data Liftoff. Prior roles include Director of Data Science at Degreed, Director of Insights & Analytics at O'Reilly Media, and Manager on the Analytics Team at Wayfair.


Thursday August 22, 2019 2:00pm - 2:45pm
Room 306 595 Commonwealth Avenue, Boston, MA 02215, USA

2:00pm

Enterprise Studio Collections: Machine Learning at Scale
The Disease Prediction and Progression OptumIQ Studio Collection contains over 200 models built to allow earlier detection of at-risk individuals, enabling providers to intervene more effectively, among many other use cases. These models span two lines of business, four modeling domains, and 25 distinct conditions. In order to build this Collection, we first needed to construct a generalized modeling framework. Leveraging the Customer Reporting Mart data and the cloud-computing resources made available via the OptumIQStudio Workbench, we developed a scalable modeling pipeline, reducing the time required to train hundreds of supervised, machine learning models to a matter of days. 

Speakers
avatar for Ahmed Kayal, MS

Ahmed Kayal, MS

Data Scientist, Optum
As an Optum Data Scientist, Ahmed's work centers around the development and implementation of machine learning models in the Healthcare space. With an interest in improving patient outcomes, he is largely focused on disease progression use cases.


Thursday August 22, 2019 2:00pm - 2:45pm
Room 211 595 Commonwealth Avenue, Boston, MA 02215, USA

2:00pm

Scaling ML/AI analytic execution for production datasets
Technical overview of how we are scaling dozens of ML models to run on tens of millions of patients data using Azure, Kubernetes, and Spark. 

Speakers
avatar for John Lavoie

John Lavoie

Sr Principal Engineer, Optum
John Lavoie is a Senior Principal Engineer at Optum focused on scaling up analytics for Optum-sized datasets.  Major projects include the Analytics Common Capability and Optum IQ Studio. 


Thursday August 22, 2019 2:00pm - 2:45pm
Room 408 595 Commonwealth Avenue, Boston, MA 02215, USA

2:45pm

Break
Thursday August 22, 2019 2:45pm - 3:00pm

3:00pm

Empowering Your Organization Through Data Literacy: What it is data literacy, why I want it, and how I can help drive change?
Data is the language of business now but there is a data literacy gap. If you are a data leader, data scientist, or data analyst then lack of data literacy results in friction, frustration, and delay. If you are a business leader or technology leader then your team's data literacy is a must for your team to be effective. Come learn what data literacy is, why you want it, and how you can act to help achieve it.

Speakers
avatar for Dave Mathias

Dave Mathias

Data Coach // Director, Beyond the Data // MinneAnalytics
Dave combines his passions around data, experience, and community to make impact. Founder of Beyond the Data, co-host of Data Able podcast, and part of MinneAnalytics and TC Data Viz Group. 


Thursday August 22, 2019 3:00pm - 3:30pm
Room 211 595 Commonwealth Avenue, Boston, MA 02215, USA

3:00pm

Where are enterprises on becoming truly data-driven, and what are "power-users" doing differently to get ahead?
This session will highlight findings from a research study about the emerging use of data and analytics as strategic business assets. Including insights from 262 enterprise decision makers across the Global 2000, we will present a nuanced view into the strategic imperatives around data, advanced analytics, and machine learning; the current and planned use of smart analytics; the main challenges along each step of the evolution; and emerging best practices of high performing enterprises in developing true, data-driven businesses. 

Speakers
avatar for Reetika Fleming

Reetika Fleming

Research Vice President, HFS Research LLC
Reetika Fleming leads research coverage for the broad use of data and analytics within enterprises, with a focus on emerging strategies to institutionalize machine learning and other AI techniques.


Thursday August 22, 2019 3:00pm - 3:30pm
Auditorium 595 Commonwealth Avenue, Boston, MA 02215, USA

3:00pm

Patient centric AI: Saving lives with ML driven hospital interventions
This presentation will cover the use of machine learning for maximizing the impact of a hospital readmissions intervention program. With machine learning, clinical care teams can identify and focus their intervention efforts on patients with the highest risk of readmission. The talk will go over the goals, logistics, and considerations for defining, implementing, and measuring our ML driven intervention program. While covering some technical details, this presentation will focus on the business implementation of advanced technology for helping people live healthier lives. 

Speakers
avatar for Miguel Martinez

Miguel Martinez

Data Scientist, Optum
Miguel Martinez is a Data Scientist at Optum Enterprise Analytics. Relied on as a tech lead in advancing AI healthcare initiatives, he is passionate about identifying and developing data science solutions for the benefit of organizations and people. 


Thursday August 22, 2019 3:00pm - 3:30pm
Rooms 426 / 428 / 430 595 Commonwealth Avenue, Boston, MA 02215, USA

3:00pm

Deep Learning for Radiology Text Report Classification
In this talk, I will discuss about our proposed advanced deep learning models for classifying free text radiology reports based on the presence of pulmonary emboli (PE). The models are trained on a subset of Stanford training set (2512 reports) and evaluated on reports collected from four major healthcare centers. Our experiments suggest feasibility of broader usage of neural networks in automated classification of multi-institutional imaging text reports for various applications including evaluation of imaging utilization, imaging yield, and clinical decision support tools. 

Speakers
avatar for Sadid Hasan, PhD

Sadid Hasan, PhD

Senior Scientist (Tech Lead), Philips Research
Sadid Hasan is a Senior Scientist (Tech Lead) of the Artificial Intelligence Group at Philips Research, Cambridge, MA. His recent research focuses on solving NLP problems related to Information Extraction and Text Classification using Deep Learning. 


Thursday August 22, 2019 3:00pm - 3:30pm
Room 406 595 Commonwealth Avenue, Boston, MA 02215, USA

3:00pm

Experiences in using data science and machine learning tasks for K-12 education
In this presentation, attendees will learn how the K-12 education sector can use classification tasks such as decision-trees to uncover new insight about students. Various linear regression models, and even failed experiments will also be discussed and what we have learned from them.  Since the use of machine learning and data science is relatively new in K-12 education space, I plan on discussing the challenges of the skill gap and introducing these concepts to the decision-makers within the education space. 

Speakers
avatar for Rich Huebner

Rich Huebner

Director, Data Science & Architecture, Houghton Mifflin Harcourt
Dr. Huebner has held both industry and academic roles for the last 20+ years that have centered around business intelligence, data science, and analytics solutions. He also teaches MBA and doctoral classes at New England College of Business.


Thursday August 22, 2019 3:00pm - 3:30pm
Room 404 595 Commonwealth Avenue, Boston, MA 02215, USA

3:00pm

Deep Learning Framework for Joint POI discovery & Scene Classification of ground level imagery
We propose a Deep Learning framework that focuses on the utilization of geotagged ground-level imagery for the purpose of scene classification and accurate identification of Points of Interest (POIs) categories (e.g. restaurants, hotels, and schools, etc.) so as to augment efforts in improving location intelligence, such as context-aware POI mapping and for improving land use classification. 

Speakers
avatar for Seema Chouhan

Seema Chouhan

Data Science Manager, Genpact
Seema is currently a machine learning research associate at ORNL. She pursued her B.S. & M.S. in Chemical Engineering from Indian Institute of Technology Delhi and pursued M.S. in Environmental Science from the University of Massachusetts Amherst.


Thursday August 22, 2019 3:00pm - 3:30pm
Room 306 595 Commonwealth Avenue, Boston, MA 02215, USA

3:30pm

Break
Thursday August 22, 2019 3:30pm - 3:45pm

3:45pm

The Evolving Data Science Landscape
Data scientists are in demand, but there still exists a disconnect between what training is received, and what jobs are looking for.  2019 data from the field is presented and an updated model for training and partnership is discussed.

Speakers
avatar for Robert McGrath, MS, PhD

Robert McGrath, MS, PhD

Director and Chair, Analytics and Data Science, University of New Hampshire
McGrath is a professor of analytics, data science and health management. His research focuses on the evolution of data science and progression of the field in practice. He has also examined the use of health data as it affects policy and practice.


Thursday August 22, 2019 3:45pm - 4:15pm
Room 404 595 Commonwealth Avenue, Boston, MA 02215, USA

3:45pm

Using Ontologies to Power AI Systems
There’s a great deal of confusion about the role of a knowledge architecture in artificial intelligence projects. Some people don’t believe that any reference data is necessary. But in reality reference data is required- even if there is no metadata or architecture definitions outside defined externally for an AI algorithm, someone has made the decisions about architecture and classification within the program. However, this will not work for every organization because there are terms, workflows, product attributes, and organizing principles that are unique to the organization and that need to be defined for AI tools to work most effectively.   

Speakers
avatar for Seth Earley

Seth Earley

CEO, Earley Information Science
Seth Earley is a published author and public speaker about artificial intelligence and information architecture. He wrote “There’s no AI without IA” which has become an industry catchphrase used by a number of people including Ginny Rometty, the CEO of IBM.


Thursday August 22, 2019 3:45pm - 4:15pm
Room 406 595 Commonwealth Avenue, Boston, MA 02215, USA

3:45pm

Building a Financial Scorecard using Python
Financial Scorecards are used widely in all financial organizations for different kinds of ratings. This talk will take you through the building and validation process of a financial scorecard using data.Financial Scorecards are used by banking organizations to judge the financial stability of their portfolio and take business decisions. These scorecards help in tracking and collections.

This talk is designed for audience to take them through the process of developing a scorecard using Python. The workshop will guide you through the EDA process using Python and will demonstrate the different kind of visualizations that can enable better data understanding. We aim to cover step by step process of building a scorecard and Use of different Machine Learning algorithms to build a better scorecard by comparing the outputs of different algorithms. We will demonstrate 3 different Machine learning algorithms Random Forest , Support Vector Machine and Gradient Boosting and their outcomes while building this scorecard.

Speakers
avatar for Nirav Shah, MS, MBA

Nirav Shah, MS, MBA

Founder, OnPoint Insights
Nirav Shah is the Founder of OnPoint Insights. He has 15 years of industry experience - mainly in consulting on data analytics, big data modeling, process analytics and real-time data solutions.


Thursday August 22, 2019 3:45pm - 4:15pm
Room 211 595 Commonwealth Avenue, Boston, MA 02215, USA

3:45pm

Recommendation systems modeling
This presentation will go over some key components of successful recommendation system building, including algorithm selection, accuracy metrics selection and other modeling aspects applicable across multiple industries.

Speakers
avatar for Lily Lavitas

Lily Lavitas

Senior Data Scientist, TripAdvisor
Lily Lavitas is a Data Scientist with a Ph.D. in Statistics and 8+ years of professional experience in various companies, including a start-up, a Fortune 100 company, and Amazon.


Thursday August 22, 2019 3:45pm - 4:15pm
Rooms 426 / 428 / 430 595 Commonwealth Avenue, Boston, MA 02215, USA

3:45pm

The NPU Era
Behind the use of artificial intelligence capabilities is a new and foundational piece of technology: the Neural Processing Unit. These AI-only processors are changing the rules for machine learning power and affordability, creating new and ideal conditions for intelligent devices. In this talk, we will explore the history, recent breakthroughs, and future impact, covering everything you need to know about the Age of the NPU. 

Speakers
avatar for Dan Abdinoor

Dan Abdinoor

CEO & Cofounder, Fritz
Dan Abdinoor is CEO and Cofounder of Fritz, an AI platform that enables mobile apps to see, hear, sense, and think. Dan leads teams in the Boston tech startup community, and previously scaled businesses at HubSpot, BabbaCo, Wyth, and Jana.


Thursday August 22, 2019 3:45pm - 4:15pm
Room 306 595 Commonwealth Avenue, Boston, MA 02215, USA

4:15pm

Networking Social in Atrium
Complimentary beer, wine, and snacks.

Thursday August 22, 2019 4:15pm - 5:15pm