Interactive CMA & Realtime Valuation

Architected and led the end-to-end development of an interactive Comparative Market Analysis (CMA) platform with Realtime Valuations, Property Embeddings and Comps API, providing agents and buyers with data-driven tools to support home pricing, enhancing client decision-making and driving potential revenue through valuation services.

Zestimate Infrastructure Modernization

Led the modernization of a critical valuation ML infrastructure, transitioning to more cost-effective, containerized technologies, resulting in substantial annual cost savings and enhanced system scalability.

Technical Innovation & Team Collaboration

Integrated advanced machine learning tools into team workflows and established coding standards, significantly enhancing collaboration and experiment tracking capabilities. Contributed to open-source projects.

Leadership & Mentorship

Managed interns and Mentored new hire, fostering technical skill development and guiding them through project contributions.

Discount Optimization

Lead the efforts to optimize subscription pricing(discounts) to maximize the revenue for OKCupid, Implemented end-to-end ML pipelines, feature engineering, modelling, alerting etc.

Speaker Identification

Developed a system to identify speakers from live audio during company calls (e.g., earning calls) using spectrograms and CNN-based deep learning models.

Private Company Fact Extraction

Led the development of a system to extract full company names, key people, their titles, and biographies from 1.6 million crawled and cached websites of private companies.

Similar Concepts & Type Ahead

Developed concept suggestion system based on queries extracted from news articles and PDF reports. Implemented distributed trie-based autocomplete/auto-suggest feature for the FactSet terminal.

Trending Topics & Formula Ranking

Built system to identify trending topic clusters from recent news articles. Developed user clustering and formula ranking system for the type-ahead feature of FactSet terminal.

Duplicate Document Identification

Duplicate Document Identification

Developed a service to identify duplicate documents in real-time from a large stream of documents using shingling and vector space models.

Earnings and Stock Correlation Analysis

Built a system to analyze correlation between social media sentiments and company earnings/stocks using logistic regression.

Time Series Analysis on Big Data

Worked on a research project involving stream fusion and time series analysis of sensor data. Responsible for conceptualizing and implementing various algorithms involving interdependent causality detection, pattern mining to extract interesting information and patterns.

Data Harmonization Framework (DHF)

Implemented the next generation ETL framework that exploits the power of map-reduce and big-databases to fuse incongruous enterprise data from disparate sources in near real time to give one harmonized view of the data and thus making analytics simpler and faster.

Conceptualized an end-to-end ETL tool built over DHF capable of generating Apache Pig scripts useful for making Harmonization process easy and seamless.

Trainee Evaluation System

Led team of two in the development of 'Trainee Evaluation System' deployed in the TCS Trivandrum training center. Created the whole system from scratch using PHP and jQuery, and was responsible for integrating 'Moodle' into this evaluation system.

Resource Planning and Scheduling System

Developed solution for the long standing problem in the training center of managing resources and scheduling them in optimal and fail-safe way. Also worked as a guest author in the "Linux and FOSS" section of the training material.