Lubricants play a crucial role in various industries such as automotive, manufacturing, and energy, where accurate demand forecasting is essential for maintaining efficient supply chains, reducing costs, and ensuring timely product availability. This study evaluates the performance of traditional time series forecasting models on forecasting of lubricants demand, with a specific focus on demand exhibiting a linear increasing trend as a prevalent pattern in many situations. The models tested include ARMA, ARIMA, SARIMA, and Triple Exponential Smoothing (TES), which are widely used for forecasting in scenarios with linear and seasonal patterns. Two datasets were selected based on their linear trend characteristics, representative of the steady and consistent growth in demand for lubricants across different industries. The datasets were split into training and test sets, with model parameters optimized to minimize the Akaike Information Criterion (AIC). Performance was measured using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Results showed that SARIMA consistently outperformed the other models, with TES, ARIMA, and ARMA following in effectiveness. The study highlights the significance of accurate lubricants demand forecasting in improving supply chain efficiency. Furthermore, the presence of a linear increasing trend in demand data underscores the importance of selecting appropriate models that can effectively capture and project these trends, which are vital for informed decision-making in supply chain management of lubricant industries.