This thesis compares the forecasting performances of FBProphet, Holt Winters' Exponential Smoothing, and Box Jenkins ARIMA models for retail sales in the US. Mean Absolute Percentage Error (MAPE) is used as the evaluation metric for comparing the forecasts in two different scenarios. The study aims to assess if FBProphet outperforms traditional econometric models in terms of forecasting accuracy. The findings shed light on the relative strengths and weaknesses of these models and contribute to improving retail sales forecasting methodologies.
Time Series Forecasting for Retail Sales: A Comparative Study of Traditional Econometric Models and a Machine Learning Approach
WARSI, NOOR HUSSAIN
2022/2023
Abstract
This thesis compares the forecasting performances of FBProphet, Holt Winters' Exponential Smoothing, and Box Jenkins ARIMA models for retail sales in the US. Mean Absolute Percentage Error (MAPE) is used as the evaluation metric for comparing the forecasts in two different scenarios. The study aims to assess if FBProphet outperforms traditional econometric models in terms of forecasting accuracy. The findings shed light on the relative strengths and weaknesses of these models and contribute to improving retail sales forecasting methodologies.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
Warsi_Noor Hussain.pdf
accesso aperto
Dimensione
3.42 MB
Formato
Adobe PDF
|
3.42 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
Utilizza questo identificativo per citare o creare un link a questo documento:
https://hdl.handle.net/20.500.12608/54687