This is a machine learning project designed to forecast the sales of Rossmann Stores. We use a variety of machine learning methods to model the historical sales data of 1,115 Rossmann stores with the goal of predicting the sales for the next 6 weeks or more.
The project revolves around the application of the following Machine Learning methods:
- Regression Techniques: Suitable for predicting a continuous quantity.
- Time Series Analysis: The sales data is a time series with potentially complex temporal structures.
- Ensemble Methods: Combining predictions from multiple models can often yield better results.
The dataset we use is comprehensive, detailing a variety of factors such as the location of the store, the number of competing stores nearby, and the current and past promotions. A more detailed description of the data can be found in the original database, which can be accessed here.
The expected outcome of this project is to predict the store sales accurately, helping the company to manage inventory and workforce efficiently. Additionally, the powerful predictive models developed here could be adapted to predict other quantities or used in other retail scenarios.
To run this project locally, follow the instructions below:
- Clone the repository to your local machine using the following command:
repo clone https://github.com/ViniciusRaphael/DSemProd.git-
Install the necessary dependencies as listed in the requirements.txt file.
-
Run the script
main.pyto start the predictive modeling.
Find out more about my work on Linkedin or check out my Curriculum.
This project is licensed under MIT licence.