Skip to content

Latest commit

 

History

History
34 lines (28 loc) · 874 Bytes

README.md

File metadata and controls

34 lines (28 loc) · 874 Bytes

=======

Demand forecasting with python

Develop a software that allows you to :

  • Make commercial forecasts from a history
  • Compare several forecasting methods
  • Display the results (forecasts and comparison)

Forecasting algorithm(s) used:

  • Single, double and triple exponential smoothing with parameter optimisation
  • ARIMA to compute a statistic model
  • LSTM, a deep learning model

Features

  • Give the decision-maker the choice of which algorithm(s) to use
  • Propose default settings, and give the decision maker the decision maker to change the parameters

Requirements

  • Pillow==8.1.0
  • matplotlib==3.3.3
  • pandas==1.2.0
  • PyQt5==5.15.2
  • PyQt5-stubs==5.14.2.2
  • pyqt5-tools==5.15.2.3
  • pyqtgraph==0.11.1
  • scipy==1.6.0
  • sklearn==0.0
  • statsmodels==0.12.1
  • tensorflow-keras==1.12.0
  • XlsxWriter==1.3.7

python version for this project: 3.7.4

=======