SURABHI SETH

• Execution of data science projects across multiple game teams
• Role involves end to end deployment of data science projects and a deep understanding of game

Projects:-

• Slots Machine Recommender Engine (Slots Games): Built a recommendation engine to suggest relevant machines to players. Used a combination of Collaborative and content based recommender system
• Development of Segmentation Platform: Built an API to facilitate the segmentation automation. It supported Data preprocessing , multiple Algorithms and Cluster Profiling
• Cheater Identification (Farmville Games) : Built a cheater identifier Pipeline using Isolation trees and helped team to minimize False Positives and maximize the True Positives
• Lapser Model (Farmville Games): Developed Lapser Model to identify the players who are at the risk of lapsing out from the game. Achieved an Precision of around 85% with the help of Random Forest Algorithm

Responsibilities:

• Consultant to various multi-national clients in developing data science solutions to their business problems.
• Role involves understanding business problem faced by client, identify data requirements, ETL , design and implementation of models , presentation of results.

Key Projects: Adidas, Japan: Customer Segmentation

• Segmentation to identify distinct customer groups and their characteristic features enabling custom promotional campaigns.
• Used clustering algorithms to identify segments of customers.

Panera Bread, USA: Recommendation engine for Catering Customers

• Built cross-sell Recommender system in big data environment for catering customers of Panera Bread
• Used Item-Item based collaborative filtering as part of Recommender system
• Developed a method to assess the quality of recommendation

Land O’ Lakes, USA: Sales prediction and Market Mix Modelling

• Predicted Dealer sales from shipment data. Market Mix Modelling on sales to calculate ROI from advertisement channels
• Used algorithms like XGBoost and Random Forest for regression.

Responsibilities:

• Part of Data Science team leading machine learning and business analytics initiatives for airline ecommerce major Cleartrip
• Role involves designing and implementation of models using prediction, classification and customer segmentation algorithms

Key Projects:Prediction of user propensity to book a flight ticket

• Predicted real time propensity of a customer to book airline ticket
• Used various classification algorithms like logistic regression, random forest and neural network to build the model

Customer segmentation using advanced clustering algorithms

• Customer segmentation through advanced clustering algorithms such as K-means & Dbscan
• Developed a modified version of K-means algorithm for better results and efficiency

Developed Content based recommender system for hotel search

• Developed a recommender system to suggest similar hotels to customer
• Used KNN algorithm to find similar hotels

• Member of R&D team working on vehicle assembly related analytical solutions Key Projects: Sentiment analysis of vehicle reviews using NLP Sentiment analysis of vehicle reviews posted on various sites like mouth shut

• Part of analytics team at Mahindra working on projects related to automobile safety and performance
• Key project included building regression model to predict mileage of a vehicle in real world usage