Debanjana Banerjee
|
Data Scientist
Walmart |
|
Debanjana is a Data Scientist at Walmart Global Tech, India. At Walmart, she has been instrumental in building numerous ML-driven solutions in the compliance space dealing heavily in Natural Language Processing, Optimization, Mixture Models and Rare Time Series. Currently, her focus is on Site Content Recommendation for Walmart.com which utilizes NLP & Computer Vision for automated shelf curation. During her 4 years of experience, Debanjana has filed several US patents in the field of Clustering & Outlier Detection, Imbalance Text Classification, Travel Optimization and Stochastic Processes. In addition, she has three published papers to her credit. Most recently, her work in Anomaly Detection for Rare Time Series was included in ODSC Europe and APAC. Debanjana has a master's degree in Statistics from Indian Institute of Technology (Kanpur).
|
Workshop: Evolution of Applied Recommender Systems
Prerequisite: Basics of Linear Algebra and Linear Algebra for Regression; Concept of Features, Response & Parameters; Basics of Clustering and Neural Networks.
Machine learning driven Recommender Systems are undeniably one of the most crucial applications in modern technology. In this age of information, we are all in business with matching people to products, services, interests, information – you name it. Today, we depend on search engines and websites to show us what we like even before we know it! But the state-of-the-art Recommender Systems we know today are a result of consistent research taking shape for over three decades. In this workshop, we take you through the whirlwind journey of the recommender system from GroupLens in the 1990s, Content Based Filtering, Matrix Factorization and Hybrid Recommender Systems in the late 2000s all the way to DeepLearning based recommenders of today.
Machine learning driven Recommender Systems are undeniably one of the most crucial applications in modern technology. In this age of information, we are all in business with matching people to products, services, interests, information – you name it. Today, we depend on search engines and websites to show us what we like even before we know it! But the state-of-the-art Recommender Systems we know today are a result of consistent research taking shape for over three decades. In this workshop, we take you through the whirlwind journey of the recommender system from GroupLens in the 1990s, Content Based Filtering, Matrix Factorization and Hybrid Recommender Systems in the late 2000s all the way to DeepLearning based recommenders of today.