MS's repositories
HackTheNorth-Won-Bloomberg-s-FinTech-Hack-Challenge
Three machine/deep learning models were developed in this hack: An LSTM RNN to predict the stock movements - A web crawler that uses sentiment analysis on returned articles - A classification model trained to differentiate between news headlines
Intraday-data-puller
This code pulls 1-minute snapshot data for NSE-CASH stocks and saves them in their respective files .The data is pulled in d,c,h,l,o,v format and converted to date,time,o,h,l,c,v format
StockForecast
Predicts the stocks using historical data + Twitter sentiment + Yahoo News + Technical Analysis
AIDeveloper
GUI-based software for training, evaluating and applying deep neural nets for image classification
AMS-Automated-home-system
System for utilizing data from the new electrical meters in Norway
AmsToMqttBridge
Minimalistic system to read AMS/HAN data from electrical meter
AmsToMqttBridge-1
Minimalistic system to read AMS/HAN data from electrical meter
ArmstrongII
Here goes the Description
Clairvoyant
Software designed to identify and monitor social/historical cues for short term stock movement
Deep-SORT-YOLOv4
People detection and optional tracking with Tensorflow backend.
Document-Image-Classification-with-Intra-Domain-Transfer-Learning-and-Stacked-Generalization-of-Deep
RVL-CDIP could be looked at as the equivalent of ImageNet for the document image community. It’s certainly the largest we’ve seen in the literature. There are 400,000 total document images in the dataset. The dataset contains much noise and variance in composition of each document class. Uncompressed, the dataset size is ~100GB, and comprises 16 classes of document types, with 25,000 samples per classes. Example classes include email, resume, and invoice. Achieved an Accuracy of over 93% which beat the benchmark score of 92% based on https://paperswithcode.com/sota/document-image-classification-on-rvl-cdip
documentarist
Process Caltech Archives' digital documents and photos, and annotate each page or image with information about its contents
GetOldTweets-python
A project written in Python to get old tweets, it bypass some limitations of Twitter Official API.
keras-yolo3
A Keras implementation of YOLOv3 (Tensorflow backend)
Multi-Camera-Live-Object-Tracking
Multi-camera live traffic and object counting with YOLO v4, Deep SORT, and Flask.
mxnet-the-straight-dope
An interactive book on deep learning. Much easy, so MXNet. Wow.
python-webinar
Webinar slides and notebook
risk-premia-app
Simple Risk Premia Strategy
robot_wealth
Work from Robot Wealth bootcamp on FX
trading-strategy-backtest
Backtesting of different trading strategies by applying different Modern Portfolio Theory (MPT) approaches on long-only ETFs portfolios in Python.