Skip to content
View mohakapoor's full-sized avatar

Highlights

  • Pro

Block or report mohakapoor

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mohakapoor/readme.md

Mohak Kapoor

Backend and AI Engineer. mohakapoor.in · LinkedIn

  • Built CodeAtlas — an agentic RAG engine that indexes an entire GitHub portfolio by topic, with hybrid retrieval (dense + BM25 + cross-encoder reranking) and a dual-agent LLM-as-judge eval framework. Context recall 0.48 → 0.83.

  • Built METR — a quant meta-labeling research framework on 3,400+ days of multi-asset Indian market data. Sharpe 1.48, validated at p<0.05 across 10k Monte Carlo simulations.


Pinned Loading

  1. METR METR Public

    METR is a controlled empirical study designed to investigate whether structured machine learning models can outperform pure randomness in short-term asset allocation.

    Jupyter Notebook 1

  2. CaptchaOCR CaptchaOCR Public

    A PyTorch-based CAPTCHA recognition system using synthetic data generation and CTC-based sequence modeling. Built with deep learning techniques, achieving high accuracy on complex text recognition …

    Python 1

  3. Network_Anomaly_Detection_CICIDS2017 Network_Anomaly_Detection_CICIDS2017 Public

    A machine learning pipeline for detecting network anomalies and cyber attacks using the CICIDS2017 dataset.

    Jupyter Notebook

  4. CodeAtlas CodeAtlas Public

    Python