Predictive forecasting in supply chain planning is a critical tool that allows organizations to anticipate demand, optimize inventory, and improve overall operational efficiency. Time-series models are commonly used for predictive forecasting because they rely on historical data patterns to predict future demand. These models assume that past behavior, including trends, seasonality, and cyclical patterns, can provide insights into upcoming periods. Classical time-series models include moving averages, exponential smoothing, and ARIMA (AutoRegressive Integrated Moving Average). Moving averages smooth out short-term fluctuations to highlight longer-term trends, whereas exponential smoothing assigns exponentially decreasing weights to older observations, allowing the model to respond more quickly to recent changes. ARIMA models are more sophisticated, combining autoregressive terms, differencing to achieve stationarity, and moving average components to account for residual patterns. Seasonal ARIMA (SARIMA) models extend this approach to include seasonality, which is particularly relevant for retail and manufacturing industries where demand cycles recur annually or quarterly. Time-series forecasting can also leverage advanced machine learning methods such as LSTM (Long Short-Term Memory) neural networks, which are capable of capturing complex temporal dependencies in data that traditional models may miss. These approaches allow supply chain managers to generate probabilistic forecasts, offering not only point estimates but also confidence intervals to support risk-based decision-making. Forecasting is closely integrated with supply chain optimization through linear and mixed-integer programming techniques. Linear optimization models aim to minimize or maximize an objective function, typically cost, profit, or service level, subject to constraints such as production capacity, inventory limits, and transportation availability. Mixed-integer programming (MIP) extends linear optimization by incorporating integer decision variables, which are crucial for modeling real-world supply chain decisions such as facility location, vehicle routing, or batch production quantities. For example, a supply chain planner may use a mixed-integer model to determine the number of trucks to dispatch between distribution centers while simultaneously optimizing inventory levels at each location to satisfy forecasted demand. Linear and mixed-integer models can also be applied for network design, production scheduling, and procurement planning, providing a systematic framework to allocate scarce resources efficiently. Scenario-based optimization can integrate predictive forecasts to evaluate the impact of varying