6-9-2019: Title: “Developing data science driven project in NLP context” Speaker: Dr. Om Deshmukh, Senoir Director of Data Sciences and Analytics at Envestnet|Yodlee

Speaker: Dr. Om Deshmukh,
Senoir Director of Data Sciences and Analytics at Envestnet|Yodlee

TITLE: Developing data science driven project in NLP context

DAY & DATE: Friday, Jan 6, 2019

TIME: 04.00 PM (Tea/Coffee at 03.45 PM)

VENUE: Seminar Hall, Department of Management Studies, IISc.

At Envestnet | Yodlee They have built and deployed several advanced state-of-the-art Machine Learning solutions which process millions of financial transactions on a daily basis with very stringent service level commitments. These transactions originate from thousands of different sources and have a wide variety of diverse structures and intent. In this session, Speaker will elaborate our framework for developing and deploying data-science driven products in the context of natural language processing of financial data. Learnings from this ML-driven product deployment will help ML practitioners and data science leaders on how to structure their ML projects, how to build an optimal prototype, and how to quickly scale from the prototype stage to the production deployment stage. Specifically, Speaker will talk about best practices and challenges for each stage of the data driven product development starting from (a) data gathering, cleaning and normalization, (b) incorporating domain expertise, (c) choice of model, (d) model training and evaluation, (e) design decisions for at-scale deployment, (f) planning for redundancy, (g) continuous monitoring for model deterioration, and (h) logging customer feedback. With the latest advancements in Machine Learning methods like deep learning and the availability of vast amount of data, there has never been a better time to build data science driven products!

About the Speaker:
Dr. Om Deshmukh is the senior director of data sciences and analytics at Envestnet|Yodlee since Month year. Om leads a team of data scientists who drive foundational data science initiatives to mine actionable insights from data for clients of Envestnet | Yodlee. His team is also responsible for creating end-to-end data science driven solutions and its delivery to clients. Om has deep expertise in theoretical and applied machine learning, and data analytics in bayesian non- parametrics and generative models coupled with deep neural networks. Prior to Yodlee, Om worked with Xerox Research and IBM Research. At Xerox Research, Om built a team of highly motivated researchers and developers and designed state-of-the-art machine learning and multimedia (speech/text/video) data analytics algorithms. He successfully spearheaded an innovative revenue sharing model with a leading edtech startup to build multimedia analytics into their products. At At IBM, Om led the Global Technology Outlook for analytics-driven billion-dollar business in ‘personalized learning’ which was then presented to the IBM CEO. Om has over 50 patents (filed/granted) to his credit and two of his patents are regarded high-value. He has also authored articles and papers for over 50 international publications, many among them are awarded best paper in conferences and publications. Om received his PhD from the department of Electrical and Computer Engineering University of Maryland, MS from Boston University and BTech from BITS Pilani.In 2017, Om received recognition as one of the top 10 data scientists in India: https://analyticsindiamag.com/top-10-data-scientists-india-2017/. Om is an active speaker in global academic conferences, guest faculty in various premier engineering colleges in India and serves as an external evaluator for BTech/MTech/PhD projects.