Hello there! I'm Tanish

I'm a Data Scientist and Applied AI Engineer building AI-powered systems for finance, analytics, and real-world decision-making.

My work focuses on financial data automation, forecasting, machine learning, explainable AI, and scalable data products — helping transform complex data into actionable insights and intelligent workflows.

What I've been working on

Prosperity Trading Terminal

A Bloomberg-style trading terminal and research platform for the IMC Prosperity algorithmic trading competition, supporting tick-by-tick market replay, strategy backtesting, order book visualization, execution simulation, and real-time performance analytics.

AI Adoption Value Realization Dashboard

An executive Power BI system that turns a two-year, $4M enterprise AI adoption strategy into a tracked value-realization layer, modeling spend, revenue uplift, payback, KPI gates, roadmap progress, scenario NPV, and program risk for a $75M CPG e-commerce business.

MatchOdds AI

An agentic RAG system for NBA pre-game betting analysis that aggregates statistics, injuries, odds, historical matchups, news, and sentiment signals, then compares CoT, ReAct, and multi-agent reasoning strategies for calibrated game prediction.

Dynamic Resource Allocation in Cloud Computing

A power-aware, SLA-bound deep reinforcement learning scheduler for cloud computing, built with a custom Gymnasium simulator, PyTorch RL agents, FastAPI orchestration, and a React monitoring dashboard.

Data Valuation for Sparse Surface Ocean Carbon Data

A Shapley-based data valuation pipeline for sparse surface ocean carbon prediction, ranking climate and Earth system data sources by their marginal contribution to regional fCO₂ prediction performance.

StressTester: AI-Assisted Financial Stress Testing Engine

An end-to-end Next.js application that combines deterministic financial simulations with a 4-stage AI pipeline to extract assumptions, generate stress scenarios, compute KPI deltas, and produce mitigation playbooks for enterprise finance teams.

Agentic NLP-to-SQL: Secure Multi-Agent Analytics Copilot

A security-first, multi-agent natural language to SQL system with clarification, schema grounding, accounting-aware query generation, and safe execution across SQL backends

Statistical Arbitrage: Factor-Based Mean Reversion Trading System

A multi-factor statistical arbitrage framework using PCA-based factor models, residual mean reversion, and systematic trade analytics

FX-Cross: Machine Learning–Driven Trading Signal Generation

Probabilistic FX trading strategies using time series smoothing, machine learning, and deep learning models

Paperchase AI — End-to-End Financial Intelligence Platform

A comprehensive financial intelligence platform

Predictive Maintenance in SCANIA Trucks

Mitigating failures by using Federated Learning and Explainable AI

Advanced Time Series Forecasting

Time Series Forecasting with Exogenous Variables for Restarurants Globally

Margshala

AI Career Assistant for Rural people

Demystifying Defects

Federated Learning and Explainable AI for Semiconductor Fault Detection

Prognosis Assistant and Appointment Scheduler

A comprehensive web application to assist in pre-doctor visit health analyses and streamline in-app appointment scheduling.

Posture Correction using Computer Vision

DL and ML Approaches for Real Time Posture Detection and Correction

FL for State of Charge Prediction

Data-Driven SoC Forecasting in Electric Vehicles: A Federated Learning Perspective

Explore My Research

Industrial Research

Demystifying Defects: Federated Learning and Explainable AI for Semiconductor Fault Detection

Lead Author

A novel semiconductor fault detection framework that combines Federated Learning and Explainable AI to enable high-accuracy, privacy-preserving, and interpretable defect classification across decentralized datasets

Federated LearningExplaianable AIFault DetectionEdge Intelligence

Undergraduate Thesis

Impact of Digital Transformation on Mental Health of IT Professionals

Principal Investigator

An explainable machine learning framework that predicts technostress and burnout in IT professionals using hybrid survey-synthetic data and SHAP-based insights to support proactive mental health interventions.

Explainable AIStress DetectionDigital TransformationMental Health

Smart Grid and Electric Vehicles

Data-Driven SoC Forecasting in Electric Vehicles: A Federated Learning Perspective

Co-Author

A data-driven State of Charge forecasting framework for Electric Vehicles that leverages Federated Learning and ensemble machine learning to deliver privacy-preserving, accurate, and scalable battery state estimation across decentralized sources

Federated LearningElectric Vehicles (EVs)State of Charge EstimationPrivacy-Preserving ML

Cybersecurity and Smart Infrastructure

Enhancing Cybersecurity in Internet of Vehicles: A Machine Learning Approach with Explainable AI for Real-Time Threat Detection

Lead Author

A machine learning and Explainable AI-based cybersecurity framework for the Internet of Vehicles that enables real-time, interpretable, and high-accuracy threat detection while ensuring model transparency and operational reliability in connected vehicular networks.

CybersecurityInternet of VehiclesMachine LearningPrivacy-Preserving ML

Tech Stack