CO: ” Evaluate Forecasting methods, predictability factors, and causes of error in Forecasting ”

Forum Prompt:

Looking at the organization for which you work, describe how forecasting demand is facilitated and what is being forecasted. Help us all also understand what forecasting factors (variables) affect the accuracy of forecasting and what factors (variables) cause errors. If it helps deepen your understanding, talk to someone in your organization who is involved in forecasting demand, requirements, or materials. Search out what improves the accuracy of the forecasting model used and what detracts from accuracy. This week, let’s educate each other regarding forecasting models used, causes for error, and what predictability factors re important to the accuracy of your organization’s forecasting efforts. Dig deep and let’s help each other understand how forecasting works in the real world.

Finally, in a short two or three sentence summary, assess the quality the forecasting models in your organization. Also address what could be done to improve forecasting?

Forecasting Methods, Predictability Factors, and Causes of Error in Forecasting

Name of the student

Affiliation

Course

Instructor’s name

Submission date

Forecasting Methods, Predictability Factors, and Causes of Error in Forecasting

Forecasting in an organization involves predicting the future based on present and past data through trend analysis. Demand forecasting is no different, as it involves estimating the probable demand for a product in the future (Hyndman, 2018). I work in a fertilizer manufacturing company in our area. I remember some colleagues explaining how business operations had become challenging, as the company could not identify future demand of the fertilizer at the local level. Hence, it resulted in inefficient plans and high inventories. When solving the problem, they used internal and external third-party data such as grain prices, weather forecasts, seasonality, supplier data, and geolocation to optimize fertilizer use among fertilizers in the area. Internally, they forecasted time series in the production, revenues, impact of promotional events, and profit margins for the past three years (Schatsky, Camhi, & Muraskin, 2019).

This way, an integrated and robust model was developed that is used even today. Forecasting using internal and external data helped learn farming trends, which through the model, an SKU for the local area was predicted at about 80% accuracy. Moreover, reports were generated, and the demand forecast produced a practical distributor-targeting approach. These impacts resulted in an improved decision-making process in the company. Factors that may affect foresting are both from internal and external environments. In this case, possible factors that could have contributed to the remaining 20% accuracy include the quality of audits, company’s financial statements, weather data, production, and consumer sentiments (Hyndman, 2018). Moreover, forecast errors can be sourced from the wrong calculation or measurements, evaluation parameters, incorrect general data entry, and possible false demand and supply trend patterns.

In my company, the forecasting model used is a combination of decomposed series and intervention analysis. Improving the accuracy of the model involves the presence of an ERP and cloud-based systems to ensure effective data transfer and to capture useful trends. Some factors that detract the accuracy include possible wrong demand-supply calculations and inaccurate weather data. The decomposition’s approach (decomposed series and intervention analysis) quality is high and effective, as it has been used for long in the company (Hyndman, 2018). In most cases, the results and impacts recorded are positive such as improved decision-making process, a substantial accuracy of 80%, and generation of efficient distribution-targeting methods. Improving forecasting in the company requires keenness in data entry to eliminate possible measurement errors, and improved quality of audits, financial statements, and weather reports to maximize accuracy.

References

Hyndman, R. J. (2018). Forecasting: principles and practice. Otexts.

Schatsky, a., Camhi, J., & Muraskin, C. (2019, February 28). Data ecosystems: How third-party information can enhance data analytics. Retrieved from Deloitte: https://www2.deloitte.com/us/en/insights/focus/signals-for-strategists/smart-analytics-with-external-data.html