In this project in which i worked with Mehdi Hamdoune, we developed a graphical user interface to make commercial forecasts of a company from its history, using deep learning and machine learning algorithms. On our software, we made available to the user five forecasting algorithms while evaluating their accuracy and performance in order to obtain the best forecast's result.
- Front end: PyQt5.
- Back-end: Numpy, Pandas, Matplotlib, Tensorflow, Keras, Scikit-Learn, etc.
- Forecasting methods : exponential smoothing (Single, Double, Holt-Winters) - LSTM - ARIMA.