DeepForecast

Deep Learning has advanced machine learning applications such as classification, forecasting, prediction. Especially, recurrent neural networks model such as Long Short Term Memory (LSTM) has been applied to temporal or sequential data. In this project, we will develop a model for predicting multiple time-series. Possible applications include stock price prediction, weather prediction, and crypto market prediction.

Potential resources: paper, code

Deliverables: datasets, codebase, trained models, accuracy results, web or mobile app (OPTIONAL)

The project requires programming skills in Python, PyTorch (or Tensorflow, etc.). Competent knowledge and experience in Deep Learning. Pro-active in learning new things.