Cohdhed/PharmaSolution-Sales-Forecasting

This project aims to develop a robust and accurate sales forecasting model for PharmaSolution's chain of drug stores in Nigeria. By leveraging data-driven insights, the model empowers store managers to make informed decisions and optimize their operations, leading to improved sales predictions and operational efficiency. # PharmaSolution Sales Forecasting Accurate sales forecasting is crucial for effective inventory management, resource allocation, and store operations planning. This project focuses on developing a robust and accurate sales forecasting model for PharmaSolution drug stores in Nigeria, empowering store managers with data-driven insights to make informed decisions and optimize their operations. ## Objective The primary objective of this project is to develop a robust and accurate sales forecasting model for PharmaSolution drug stores in Nigeria. This model will empower store managers with data-driven insights to make informed decisions and optimize their operations. ## Key Steps to Achieve the Objective - **Exploratory Data Analysis (EDA) and Data Visualization:** Conduct EDA to gain insights into the dataset's characteristics. Visualize data distributions, correlations, trends, and seasonality. Identify patterns that can aid in sales forecasting. - **Feature Engineering:** Create additional features to improve the model's predictive power. - **Pipeline for Data Preprocessing and Model Training:** Construct a robust data preprocessing pipeline using ColumnTransformer and Pipeline from scikit-learn. Include components such as imputation for handling missing data, encoding techniques for categorical variables, and scaling for numeric features. Prepare the data for model training by chaining all preprocessing steps and incorporating the chosen estimator. - **Data Splitting:** Split the dataset into a validation set (40%), a test set (20%), and the remaining portion as the training set, using a random state of 42. - **Model Training and Validation:** Train the sales forecasting model on the training data using Decision Tree and Random Forest algorithms. Validate the model's performance on the test data. - **Model Evaluation:** Evaluate the model's performance using RMSE (Root Mean Square Error) and R2-score (Coefficient of Determination). - **Hyperparameter Tuni …