Improving Sales Forecasting by Combining Key Account Managers’ Inputs and Models Such as SARIMA, LSTM, and Facebook Prophet

Sales forecasting is important for a company to plan its production. The quality of forecasts influences finances and the product availability. impact sales on may result an immobilization cash flow by causing high stock level, which opposite out-of-stock impact. purpose this study was find suitable model predicting best that has better accuracy or production plan. proposed method includes adjustment prediction including key account managers’ expertise as qualitative method. This analyzed using different time series techniques such exponential smoothing, seasonal autoregressive integrated moving average Facebook Prophet. These were compared in parallel with neural network approaches long-short term memory. Comparisons made root mean square error residual determine whether too optimistic pessimistic. dynamic. Adjustments inputs could directly influence values obtained quantitative methods.