Sales_Forecasting_ML_Case_Study

ML Data Preparation – E-Commerce Sales Forecasting Prepared and transformed a raw e-commerce transaction dataset for training a Sales Forecasting machine learning model using Python and data preprocessing techniques. Tasks Completed: • Cleaned and processed raw sales data • Detected and treated outliers in Qty, Price, and Discount using the IQR Capping method • Performed data quality checks and verified dataset consistency • Created engineered features including Revenue, Month, DayOfWeek, and DayOfMonth • Applied encoding techniques for categorical variables • Scaled numeric features using StandardScaler • Organized outputs into Raw Data, Cleaned Data, ML-Ready Data, and Quality Report sheets Tools Used: Python, Pandas, NumPy, Scikit-learn, Matplotlib, OpenPyXL, Jupyter Notebook Result: Converted raw e-commerce data into a clean, fully numeric, machine-learning-ready dataset optimized for sales forecasting and predictive analysis.