The thesis examines various quantitative forecasting techniques to enhance demand prediction in the valve industry. Analyzing historical sales data for five Flowserve products, the study employs methods such as Simple Average, Moving Averages, Exponential Smoothing, Holt-Winters Method, Linear Regression, and ARIMA. The performance of these techniques is evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE). Results indicate that sophisticated models like ARIMA and Linear Regression outperform simpler methods by better capturing data variability and trends. The findings suggest that advanced forecasting techniques are essential for improving inventory management and operational planning in the valve industry, offering valuable insights for industry practitioners and contributing to the broader field of demand forecasting research.