AndrewReaganM / msci_ml

Time Series Data Cleaning by Predicting Missing Data Values

Time Series Data Cleaning by Predicting Missing Data Values

The objective of this project is to predict data values that are missing from a stock dataset using various machine learning techniques.

Data Courtesy of borismarjanovic on Kaggle: https://www.kaggle.com/borismarjanovic/price-volume-data-for-all-us-stocks-etfs

Project Asset Structure

The files in this project are organized in the following structure:

src/preparation

This directory contains the data import code that is used to pull the dataset from disk into memory.

src/processing

This directory contains the data processing code that prepares the data for use with machine learning models. This code will likely be used after the code in src/preparation is used to pull the data from disk.

data/raw

This diretory contains the raw data imported from the source.

data/processed

This directory contains intermediary pre-processed data.

in progress