Stock Prediction IoT
IoT-fed real-time market monitoring with predictive price models, multi-source feature engineering, and a Streamlit analytics dashboard.
Pipeline
Architecture
End-to-end flow, stage by stage.
- 01
IoT feeds
- 02
Feature engineering
- 03
Model training
- 04
Streamlit dashboard
How it works
Created a live collection pipeline for streaming market observations and combined multiple sources into model-ready time-series features.
Covered the complete ML workflow: preprocessing, feature selection, model training, validation, and real-time predictive inference.
Presented forecasts and financial signals in a Streamlit dashboard designed to make the outputs understandable to non-technical users.
- Real-time
- IoT market data feed
- Multi-source
- Feature engineering
Stack
More projects
Computer Vision
Neural Style Transfer
Combined content and style features from CNN layers using Gram matrix texture representation and a composite loss function — foundational generative vision work.
Computer Vision
Air Canvas — AI Virtual Painter
Air-drawing interface built on skin segmentation, contour analysis, fingertip localization, and state tracking for draw, color-select, and erase tools.