Demand Forecasting for TechHub Electronics
Uploaded by
mahimatejpalsharmaDemand Forecasting for TechHub Electronics
Uploaded by
mahimatejpalsharma- Forecasting Demand
- Project Submission Introduction
- Forecast Error Calculation
- MAPE Calculation
- Bias in Forecasting
- Recommendations
- Detailed Device-Specific Recommendations
Common questions
Powered by AIEnhancing demand collaboration with retailers through systems like VMI and CPFR is proposed to improve smartwatch sales forecasts. This strategy is necessary as smartwatches showed stable yet decreasing demand against forecasts. By better aligning production with retailer insights and real-time sales data, TechHub Electronics can improve forecast accuracy, reducing overproduction and managing inventory costs effectively .
Forests for smartwatches exhibited significant forecast errors and biases, with errors worsening each month, peaking at -72.4% in June. The errors indicate that actual demand was consistently over-forecasted. The suggested improvement includes enhancing demand collaboration with retailers through a Vendor-Managed Inventory (VMI) system and implementing Collaborative Planning, Forecasting, and Replenishment (CPFR) to better align production with real-time demand insights .
The Simple Exponential Smoothing method is selected due to its simplicity and intuitiveness, requiring only one parameter, the smoothing factor, that adjusts to fit data preferences. It is suitable for short-term forecasts, which is pertinent for TechHub Electronics' six-month forecast need. Additionally, it effectively handles data sensitive to recent changes, aligning well with the observed demand data characteristics .
Forecast bias refers to the systematic error where forecasts consistently deviate from actuals, either overestimating or underestimating demand. In TechHub Electronics' case, biases are evident with smartphones generally under-forecasted, noticeable in April and May, while laptops had inconsistencies across months, and smartwatches suffered from considerable positive bias reflecting over-forecasting. Bias calculations showed negative values for smartphones and laptops (indicating under-forecasting in earlier months) and predominantly positive values for smartwatches .
A higher value of α is recommended because forecasted demand fell short of actuals, and data shows sensitivity to recent changes, implying a need to incorporate more recent demand trends into the forecast. Increasing α would make the forecasts more responsive, capturing recent variations and aligning more closely with actual demand behavior observed in laptops .
JIT inventory management minimizes carrying costs while ensuring product availability by aligning inventory levels closely with demand. For TechHub Electronics, implementing JIT can improve responsiveness to demand fluctuations for laptops, optimizing inventory to better meet actual needs while reducing excess stock and related costs .
MAPE provides a measure of forecast accuracy by averaging the absolute percent errors between forecasted and actual values. At TechHub Electronics, MAPE helps identify forecasting performance across product lines, highlighting areas with significant inaccuracies, such as smartwatches, which had high MAPE values, indicating worsening forecast accuracy over time .
Assuming a 5% variation between forecasted and actual demand introduces an anticipated margin of error into forecasts, permitting adjustments and flexibility in supply strategies. This assumption suggests forecasted values typically are lower than actual demand, which guides TechHub Electronics to prepare contingencies or maintain buffer stocks to hedge against such estimations .
The smoothing factor (α) in Simple Exponential Smoothing determines the weight of recent versus past demand data. A higher α makes forecasts more responsive to the latest changes, while a lower α results in more stable forecasts. For TechHub Electronics, using α = 0.3 suggests a balance between responsiveness and stability, appropriate for forecast adjustments based on current demand trends .
It is recommended to diversify suppliers and strengthen partnerships with multiple vendors to mitigate risks related to demand volatility and potential supply chain disruptions. This strategy helps reduce dependence on single-source suppliers, preventing delays or shortages caused by unexpected circumstances like demand spikes or supply interruptions .
