Business Context
Acme Corp, a mid-sized retail company, is looking to understand the factors influencing their monthly sales to optimize their marketing strategies. They have collected data on various features such as advertising spend, price discounts, and seasonal factors over the last three years. The marketing team needs to interpret the coefficients of a linear regression model to make informed decisions about where to allocate budget effectively.
Dataset
| Feature Group | Count | Examples |
|---|
| Sales Data | 36 | monthly_sales, advertising_spend, discount |
| Marketing Features | 5 | social_media_ad_spend, email_campaigns |
| Seasonal Factors | 2 | holiday_season, month |
- Size: 36 months of sales data, 43 features in total
- Target: Continuous variable — monthly sales revenue
- Class balance: Not applicable for regression
- Missing data: 10% missing in advertising spend due to incomplete records during some months
Requirements
- Build a linear regression model to predict monthly sales using the provided features.
- Interpret the coefficients of the model and explain their significance to the marketing team.
- Discuss how changes in advertising spend and discounts affect monthly sales based on the model's coefficients.
- Provide a summary of the model's performance using appropriate metrics.
Constraints
- The model must be interpretable, as the marketing team needs to understand the results without advanced statistical knowledge.
- The solution should handle missing data appropriately to ensure robust predictions.
