Sales Data Analytics

• published through Heroku Git

• Inspired by Dash Clinical Analytics template.

About the data

The data used in this application is bike products sales data accumulated at country and region geographical levels. Data was split into training (80%) and test set (20%) before feature scaling and no data imbalance was found.

Purpose of the application

• Develop and test different machine learning predictive and classification modellings techniques
• Compare the methods' performance metrics

Content of the application

1. Tab 1 - data description (dodge bar graph, table, map)
2. Tab 2 - regression modelling (heat map, feature importance plot and performance table)
3. Tab 3 - binary classification (confusion matrix, ROC-AUC curve, accuracy table, classification table and feature importance plot)

Screenshot of the application