Repository to analyse the time-series data from Walmart Inc found in Walmart Sales Dataset of 45 stores.
Some of the topics approached in the notebook are:
- Exploratory Data Analysis
- Autocorrelation
- Time Series Decomposition in seasonal, trend and noise
- Model training and tunning to predict Walmart's weekly sales
System to analyse the problem:
Create an automated system where the data is passed and the system finds the best ML, or statistical model (or unsemble), save the best model specifications in a database. Save best prediction in the database. Evaluations and predictions are shown in an app on the web browser with plots of:
- Prediction over training
- Prediction over test
- Two or more evaluation metrics changing for each running
- Prediction over all stores with subplots
- Training over a store and predicting over others with the same model
- Predict combined sales
- Other exploratory analysis features in the panel