<![CDATA[The rapid growth of pet ownership in Indonesia has driven a steady increase in demand for pet food products, which typically follows a recurring seasonal pattern across the year. Abadi Petshop, a local pet supply store, has so far relied on manual recording and the owner's intuition to estimate future sales, an approach that does not systematically account for historical sales patterns and frequently leads to inaccurate stock planning, resulting in either overstock or stockouts. This study aims to design and implement a web-based sales prediction system for pet food products using the Seasonal Autoregressive Integrated Moving Average (SARIMA) method, applied to monthly sales data of a Whiskas cat food product collected from January 2023 to December 2024 (24 observations). Non-seasonal differencing (d = 1) and seasonal differencing (D = 1, s = 12) were applied to achieve stationarity, and the Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF) plots were used to identify the model order, resulting in a SARIMA(1,1,1)(1,1,0)12 model with parameters φ = 0.6, Φ = 0.3, and θ = 0.4. The system was developed using the Laravel framework with a MySQL database, following the Unified Software Development Process (USDP), and functional black-box testing confirmed that all core features — including login, sales data input, prediction processing, forecast visualization, and result export — operated successfully. The resulting forecast for the twelve months following the training period projected a gradual upward trend, starting at 140.20 kg in the first month and reaching 175.50 kg by the twelfth month, consistent with the increasing trend and annual seasonal pattern observed in the historical data. These findings indicate that the SARIMA method is capable of automatically modeling trend and seasonal components in pet food sales data and can support Abadi Petshop in making more accurate, data-driven decisions regarding inventory planning and sales strategy.]]>
