8000 GitHub - cdkth/sales-forecasting: 5 machine learning techniques to forecast product sales

More Web Proxy on the site http://driver.im/

cdkth / sales-forecasting Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

5 machine learning techniques to forecast product sales

1 star 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
model_output		model_output
notebooks		notebooks
README.md		README.md
data_preprocessing.py		data_preprocessing.py
models.py		models.py
results.py		results.py

Repository files navigation

5 Machine Learning Techniques for Forecasting Sales

Objective:

Predict the number of monthly product sales using regressive and time-series modeling techniques

Featured Techniques:

EDA
Linear Regression
Random Forest Regression
XGBoost
Long Short Term Memory (artifical recurrent neural network)
ARIMA Time Series Forecasting

Results:

Best results were obtained from the XGBoost and LSTM models
All models predicted within 2% of monthly mean sales for 12 month prediction

Data Source:

https://www.kaggle.com/c/demand-forecasting-kernels-only/data

About

5 machine learning techniques to forecast product sales

Custom properties

Report repository

Releases

No releases published

Packages

No packages published

Languages

0