Jan 2025 – Present · 1 yr 3 mos · London Area, United Kingdom · Remote

Oct 2024 – Jan 2026 · 1 yr 3 mos · Remote

• Data Science Instructor for MIT Applied Data Science & AI Course

Dec 2022 – Feb 2026 · 3 yrs 2 mos · London, England, United Kingdom · Hybrid

Jan 2022 – Dec 2022 · 11 mos

Jun 2021 – Jan 2022 · 7 mos

Nov 2019 – Jun 2021 · 1 yr 7 mos

• Worked as Data Scientist level 2 of the Artificial Intelligence - COE Machine Learning Team under Enterprise Analytics and Data Science Team.
• Developed end-to-end model validation process for 3P built credit,
• debit card payments fraud models involving building benchmark ML models, model
• interpretability analysis and thorough technical documentation. Resulted in successful annual
• validation of 10 legacy fraud models for Consumer and Small Banking, Commercial Banking, Card and Claims.

Feb 2020 – Jun 2021 · 1 yr 4 mos

Nov 2018 – Nov 2019 · 1 yr

• Led a team of 5 data scientists to provide supply chain optimization solutions for a leading Food, Confectionery, and Pet-care company in the US, improving perishable inventory management efficiency to help make the lives of end consumers and commercial team easier.
• Developed a one-click robust Sales Forecasting Tool in Python using Time Series ML algorithms for a Pan-Asian Life insurance group for both Agents and Bancassurance channels, resulting in enhanced sales strategy and incentive design.
• Collaborated with Product Teams, Consumer Experience Team, Sales Team and C-suite Executives, contributing to improved decision-making processes and revenue growth.
• Algorithms used Clustering algorithms like K-means, DBSCAN, Hierarchical Clustering and Time Series ML algorithms with SARIMAX, ETS, TBATS, Prophet along with model enhancement techniques like Hyper-parameter tuning , PCA, MCA
• Tools used Tableau, PowerBI, Python, Pyspark, SQL

Oct 2016 – Oct 2018 · 2 yrs

• Search Syndication (Digital Marketing):
• Worked with World's second largest Search Engine Marketing Group and their Product team who wanted data driven analytical solution for its Syndication Ads Network to identify monetization opportunities from both supply and demand.
• Responsibilities included building scalable analytical solution framework for KPI estimation to on-board Syndication partners, building and automating dashboards to monitor performance on daily basis of both partners and advertisers, ad-hoc basis one day turnaround root cause analysis on any anomalous KPI fluctuations and advertisers escalations.
• Experimentation and A/B testing to identify monetization opportunities from both supply and demand.
• Additional responsibilities included interfacing with clients for requirement gathering, project management, stakeholder management, cross-functional team collaboration.
• In-house Analytics Team- 'Art of Problem Solving'
• Deep learning use case analysis for introducing new tools in AOPS product suits which can leverage State-of-the-art neural networks solutions
• Natural Language Processing and Text mining use case analysis for introducing predictive search feature for existing Mu Sigma patented muPDNA tool