About me
Passionate about crafting elegant solutions that make a real impact on end users. With a knack for turning complex problems into elegant, sustainable solutions through data science, I transform raw data into strategic, actionable insights.
Beyond the data realm, my entrepreneurial spirit drives me to envision a future where daily tasks are redefined, enabling people to focus on what truly matters. My ultimate goal is to integrate AI, Cognitive Science, and Robotics to create transformative solutions.
I am committed to harnessing data and technology for an innovative and meaningful tomorrow.
What i'm doing
Professionally
-
Anomaly Detection
Uncovering hidden patterns and ensuring operational reliability
Specialized in the domain of Fraud Detection, applied various models such as GBT, XGBoost, TabNet, DevNet and ConNet to identify abusive data points. In addition to models, built multiple rule-based pipelines to catch fixed fraud patterns which were identified through EDA.
Also, worked on group frauds identification by leveraging graph theory. Modelled the entities in a graph, connected them with various KPIs and applied both community detection algorithms and models such as Louvain Algorithm, Leiden Algorithm, PSO optimization, Graph Convolution Network and Deep Modularity Network. -
Propensity Modelling
Predicting customer behavior and driving strategic decisions
Dived deep into predicting the value of a new user on a platform, experimented with various custom-built neural network architectures such as MLP, SIMO & MIMO with modified loss functions. Also, applied various tree-based models built in tensorflow by leveraging TF-DF module.
Have built both classification models and regression models in which risk score and life time value are predicted respectively. -
Location Intelligence
Transforming geospatial data into actionable insights
Leveraged the GPS pings data to generate suggestions & rectify the incorrectly logged locations in the system. Designed an automated pipeline to regularly look for incorrect locations, generate suggestions and rectify. Explored multiple methods to generate suggestions such as Geometric Median, Clustering, Outlier Filtering, etc.
Also, worked on the Facility Location Identification and Demand Estimation where in post predicting the demand heatmap in a city, determine the optimal locations for the facility to cater the maximum demand and ensure profitability. Applied various constraints and optimizations from Linear Programming using the tools like Gurobi & Pulp. -
Generative AI
Revolutionizing content creation and transforming ideas into reality
Worked on an image inpainting pipeline which beautifies the dish images using stable diffusion and also adds text & gradient overlays. Utilized the ControlNet and CLIP Segmentation models from diffusers and transformers packages for inpainting.
Contributed to a in-house Text2SQL pipeline which is a multi-stage RAG pipeline, building context at each stage as its get fed more metadata and narrows down to the specific columns and tables required to generate the query. -
Operational Excellence
Driving optimizations and efficiency through data-driven strategies
Implemented various optimizations in terms of storage and compute capacity, saving thousands of dollars per month in tech cost. Understood the in-depth workings of Redis, DynamoDB, Kafka and Yack to identify the optimization opportunities.
Moreover, have designed & implemented various automations to reduce the human dependency and enable self-serve capability to the pipelines. Leveraged the APIs of Databricks, GSuite, GCP, AWS and Slack. -
Data Analysis
Unlocking the potential of data with precise and insightful analysis
Have performed varied analysis ranging from Exploratory Data Analysis (EDA) to Total Addressable Market (TAM) Sizing. This helps us guage the insights & actions from the data and its impact.
Given the experience in Anomaly Detection, Anecdotal Analysis and Root Cause Analysis are also part of my prominent skills. This helps us in explaining why a model or rule behaved like that in a particular case and also, reach an unbiased conclusion of what should have actually happened.
Personally
-
SaaS Applications
Building innovative and robust SaaS platforms
I keep looking for the pain points in day-to-day life which can be easily solved with a tech platform and try my best to make it a reality. Few of the platforms I have built in past are
Bolt - AI infused swing trading platform which takes charge of the entire trading process, from strategically selecting stocks to optimal investment allocation and timely executions on the exchange.
inDex - an open data community platform where researchers, organizations, contributors, consumers, etc can come together and help each other in piling up non existing datasets for crafting new revolutionary products.
PixelRides - a cab booking platform with bargaining capability enabled for customers & drivers to reach a satisfactory price before booking the ride. -
Trading & Investment
Crafting efficient strategies for dynamic market conditions
Always on hunt to identify and design an even-more accurate strategy which can shortlist potential stocks and provide precise entry & exit points.
Play around with a heirarichal structure of strategies from a longer time frame to the shortest time frame, like a waterfall model which can filter for only the strong choices at the end. -
Reading
Constantly expanding my knowledge from articles, blogs, and books
I like to keep myself updated with the latest things happening around me, I try to get my quick bites from articles and blogs. And when I want to learn something new or bigger, I take up books or courses. -
Retro Gaming & Shows
Exploring the charm and nostalgia to spark creativity and relaxation
Tekken-3, Mario, Sonic, Contra and Adventure Island are some of my favourite retro games.
Testimonials
