Skip to content

Sichun-Li/Machine-Learning-Nintendo-Sales-Forecasting

Repository files navigation

Machine Learning-Nintendo Sales Forecasting

The Nintendo Switch is a video game console developed by Nintendo, released worldwide in most regions on March 3, 2017. It is a hybrid console that can be used as a home console and portable device.
In this Nintendo Switch data analytics competition, the task was to forecast the US sales of Nintendo Switch in the first week of May with sales data from January, 2018 to April, 2020.

Tool: Python

  • data preprocessing and feature engineering
  • machine learning and deep learning modeling
  • cross validation based on MAE
  • weight calculation for modeling outputs based on MAE metric and final weighted result computing

Algorithms Used

  • Random Forest
  • Extreme Gradient Boosting
  • Multilayer Perceptron
  • Long Short-Term Memory

Outcome: won the first prize with predicted result most closest to actual sales

Releases

No releases published

Packages

No packages published