#time-series

Deep learning-based PM2.5 air quality forecasting using LSTM, GRU, and ARIMA to predict 24-hour ahead PM2.5 concentrations in Dhaka.

A multi-agent LLM framework for explainable algorithmic trading on NSE-listed equities — DL forecaster, LLM news sentiment, and bull/bear debate, evaluated under a full Indian transaction-cost model.

Agentic AI workforce forecasting system using Streamlit, Flask, CrewAI-style agents, LangGraph-style workflow logic, guardrails, and VET/VTO staffing recommendations.

Vending fleet operations platform - live telemetry, geospatial restock routing, depletion forecasting, and AI fault triage. MERN + MongoDB change streams, time-series, and geospatial.

Git-native forensic archive of AI provider service status. Polls OpenAI, Anthropic, and Google Cloud every 5 minutes and commits only when state changes — the git history is the time-series database.