Scroll To View More
Rahul Anand, Data Science Developer in Bengaluru, Karnataka, India
Rahul Anand

Data Science Developer in Bengaluru, Karnataka, India

Member since February 11, 2017
Rahul is a data science professional with a blend of management expertise, technical proficiency, and business acumen. He drives results with expertise in building end-to-end solutions using algorithmic bidding, experimentation framework, and relevance and model automations.
Rahul is now available for hire

Portfolio

Experience

  • R, 15 years
  • Mathematics, 15 years
  • A/B Testing, 15 years
  • Data Science, 12 years
  • Machine Learning, 10 years
  • Python 3, 8 years
  • RStudio Shiny, 3 years
  • Spark ML, 2 years
Bengaluru, Karnataka, India

Availability

Full-time

Preferred Environment

Linux, CentOS, Anaconda, R, Python, Shiny, Spark

The most amazing...

...project I've built was a scalable and robust A/B test platform where the logic could be extended to any website and optimized on any user-defined metric.

Employment

  • Principal Data Scientist

    2013 - PRESENT
    Groupon
    • Built a user-to-product recommendation system that targeted customers with email and push notifications with high precision.
    • Created a robust A/B testing framework that locates the best variant on any user-defined attribution method.
    • Developed an automated bidding system for display, and SEM marketing.
    • Built a product-to-product-based recommendation system to create greater engagement, and drive purchases.
    • Designed a model to predict the Customer Lifetime Value (540 days) after any predefined action taken by a user.
    • Developed a real-time, multi-touch attribution model to help identify the efficiency of the campaigns run by paid marketing channels.
    • Created a framework to calculate the marketing channel incrementality, that helps a business identify which campaigns generated incremental orders, and which took credit from the attribution methodology.
    • Designed a customer segmentation methodology to cluster users based on long-term profitability rather than immediate transactions.
    Technologies: R, Python, Spark, Hadoop, Shiny, Elasticsearch, Redis
  • R&D Analyst

    2012 - 2013
    Global Analytics
    • Built an automated model building platform. Given any dataset, the module will attempt to build an ensemble model for the best possible result.
    • Developed a user-defined variable generation module, which transforms the dataset based on the configuration file provided by the user.
    • Built a module for missing value imputation, which helps a dataset utilize all possible information provided, and replace missing data with a proper guess-using simulation.
    • Ran multiple ad-hoc analyses, which helped shape the business based on my recommendations.
    Technologies: R, Python, SQL

Experience

  • Product-to-Product Recommendation System (Development)

    Developed a machine learning model which resulted in a widget that presented pertinent information about a customer's buying and viewing habits. For example, this customer bought this item and also bought these items, or customers who viewed this product also viewed these things. This generated an eight percent lift in engagement and a four percent increase in total purchases.

  • Built a Multi-touch Attribution Model for a Marketing Channel (Development)

    I developed a mathematical formula that gives weight to the marketing channels for the purchases made by users. It was based on the probability distribution of the landing page and channels. This helped the finance team create a budget for all the paid marketing channel, and helped the team create more efficient campaigns.

  • Real-time Attribution Model (Development)

    I developed a framework on Spark, that helped identify the correct attribution of the order of the marketing channels in real-time. This helped us adjust the budget of inefficient campaigns to save money. Having this system work in real-time, saved millions of dollars a month by reducing the impression share of inefficient campaigns, and replacing them with the impression share of efficient campaigns.

  • User-to-Product-Based Recommendation System (Development)

    Built a deep neural network model to predict the propensity of purchases for each user towards each product available on the site. This was used in email marketing and push notifications. The model added an eight percent incremental gross profit.

  • Algorithmic Bidding (Development)

    Developed an automated system to predict how much to place on bids for each campaign on Facebook and Criteo, and bid for keywords for SEM. The system also helps select the top keywords to bid for SEM.

  • A/B Test Framework (Development)

    Created an end-to-end framework to test two variants of the product, and find the winner based on statistical techniques. It started with basic sample size calculations, Next, we ran a smoke test to identify any fundamental flaws in the system, after which we ran a calibration phase to get the impact and an even more accurate sample size. Finally, we ran the main test to get the overall lift and t-value to calculate the statistical significance. I applied group sequential analysis to end the experiment in less than the prescribed time.

  • Customer Segmentation (Development)

    Convinced top management to look at the customers based on long-term impact rather than just RFM segments. This shaped the company to look at a broader segment of users rather than simply focus on short-term gain. I built a machine learning model to predict the one-year downstream value generated by all customers, and segmented them based on the prediction. This model is being used to target customers appropriately via paid marketing channels, spend more on low-value customers to encourage them to move up the ladder, and shape their spending habits in a way that is most profitable for the business.

Skills

  • Languages

    R, Python 3
  • Frameworks

    Hadoop, Spark, RStudio Shiny
  • Libraries/APIs

    Spark ML, Tidyverse, TensorFlow, Keras, Facebook API
  • Tools

    Plotly, sparklyr, Spark SQL, Solr
  • Paradigms

    Design-driven Development (D3), Data Science
  • Platforms

    Anaconda
  • Storage

    MySQL, Apache Hive, Elasticsearch
  • Other

    Machine Learning Automation, Machine Learning, A/B Testing, Mathematics, Data Engineering, Deep Learning, Deep Reinforcement Learning, Reinforcement Learning, Statistics, Analytics, Computer Vision

Education

  • Student Research Assistant in Operations Research (Game Theory)
    2010 - 2012
    Massachusetts Institute of Technology - Boston, USA
  • Master's degree in Mathematics and Scientific Computing
    2007 - 2012
    Indian Institute of Technology - Kanpur, India
I really like this profile
Share it with others