The Forecasting Department
The forecasting department has again reported low accuracy levels of 60%, which affects how and when to run product manufacturing, order raw materials, and have enough time to package and ship products to customers without delay. As a result, the forecasting department developed a new model to achieve higher levels of accuracy. A recommended strategy is to employ causal models that use considerably sophisticated and exact data regarding relationships between structure elements and are influential enough to take various activities into account. As with the other models, the past is also an important point to be considered in the causal model.
The Causal Model
The causal model involves a system founded on the hypothesis that the dependent variable that has to be implemented has a connection with other independent variables (Causal Forecasting, n.d.). The causal model deals with the demand variability. It is a quantitative model of forecasting that combs for causes for demand and is favored when a set of variables moving the condition are presented. For example, a number of causal factors may influence the demand of the customers. Those factors include the product price, advertising cost, sales promotion, and the seasonality of the product (Benkachcha, Benhra, & El Hassani, 2013). This model is easy to develop and implement. So in our situation, if we found out or looked into history as to why and the period in which our products have a high demand, we are more likely to forecast accurately of the supply that we will need to provide so as to satisfy the consumer and reach the in the time they need the product. Even as we evaluate our advertising costs or the manner in which we intend to do sales promotion, it is easy to refer to the history of the company when the products are advertised. We can then expect an increase in sales during that time and, therefore, because of such a forecast we are able to do early orders so as to produce and package the products before the period in which they'll be advertised in the future. As a result, it makes the company prepared for the demand of goods that come with advertising and sales promotion and, thus, are able to fulfill the consumers' demands.
Problems with Relying on Forecasts
However, the accuracy of the predictions is not as important as the traditional methods since it has a tendency to be inflexible, especially in dynamic conditions that we have today. It does not allow adaptability, does not permit investigation, and does not accommodate arrangement beforehand. Consequently, there are three problems with relying on forecasts. The first one is that it is easy to obtain false data that may be accumulated from analyzing the previous trend. Secondly, is that unexpected events may occur in the course of a business financial year that may affect the forecasting terribly. In addition, forecasts become a focus for companies by representing short term to long term thus mentally limiting their range of actions. It is important to note that forecasts cannot integrate their own impact, meaning businesses are influenced by a factor that cannot be a variable.
Ordering and Shipment Schedule
Ultimately, I would do the ordering for the steel to make the widget on Monday, January 3rd, 2011 from vendor C. This is a good step to ensure that there is no rush in the manufacturing and packaging of the widget since it arrives after three weeks. On the same day, I will order the plastic cover from vendor A. This will also take three weeks to arrive. Finally, for the day, I would also make a request for the shipment of the cardboard shipping box from vendor B which will arrive four weeks after an order is made.
The plastic cover will, therefore, arrive on Monday 17th, 2011 before all the other products ordered. The arrival date of the steel used to make the widget is scheduled to be on the Monday 24th, 2011. This will be followed by the arrival of the shipping cardboard on the same day Monday 24th, 2011. On Tuesday 25th, 2011 the manufacturing of the widget commences. The widget is fully manufactured by Monday 31st, 2011. On the same day, the widget will be transported from the production department to the packaging department to await packing.
The widget is received at the packaging department on February 1st, 2011. The plastic cover is applied on the widget and it is inserted in the shipping box on February 2nd, 2011. On March 14th, 2011, the manufactured and packaged widget is sent off to the customer. This the appropriate date so that the widget neither arrives earlier than expected to the customer nor is it late. On March 31st, 2011 the widget is delivered to the customer on precisely the date he wanted it to arrive at his location.
References
Causal Forecasting. (n.d.). BusinessDictionary. Retrieved from www.businessdictionary.com/definitioncausal-forecasting.html
Benkachcha, S., Benhra, J., & El Hassani, H. (2013). Causal method and time series forecasting model based on artificial neural network. International Journal of Computer Applications, 75(7),
