Pharmaceutical-Sales-prediction

• Rossmann Pharmaceuticals is an pharmaceuticals company that has multiple stores across several cities.
• Their finance team wants to forecast sales in all their stores across several cities six weeks ahead of time.
• The data team identified factors such as promotions, competition, school and state holidays, seasonality, and locality as necessary for predicting the sales.
• The task is to build and serve an end-to-end product that delivers this prediction to analysts in the finance team.

The goal here is to design a reliable sales prediction for finance team, and give sales forcasting and response/recommendations to the finance team .

---

First we will perform EDA, and we move on to Machine Learning algorithms to find the feature importance then Finally we will build a predicting ml model using deep learning.

MLOps Design

Steps to work with this repo

1. clone the repo
2. create a new environment and install the requirements.txt
3. run dvc pull to get the dataset and model files
4. use the Notebooks/random_forest.ipynb notebook as an example for accessing data and training a model
5. use good names for the mlflow experiment name and run names. Experiment name should be prefixed with our names.(we can discuss this)