Introduction
Inventory demand forecasting is one of the most crucial part of supply chain management and the pedestal on which principles of effective and efficient inventories control lies (Cooper et al., 2007). While developing a supply chain that will have a guarantee of future sustainability and which will offer Vacumet coating company (VCC) a rather sustainable competitive advantage, Crank and William must integrate technologically assisted models that offer the company the highest degree of inventories demand forecasting accuracy and precision.
From the scenario, it is crystal clear that the current supply chain at VCC is ineffective as far as inventories demand forecasting is concerned. This is characterized by the fact that the firm is often faced with materials excesses leading to extra inventories costs and wastages, or shortages that usually call for the last minute expediting as a last gasp measure to save the company from missing customers’ needs or market demand.
While shortages of inventories poses a danger to VCC for failing to meet the market demand and customers need with a threat of customer dissatisfaction and ultimate increase in turnover, excess of inventories amounts to wastages and increment in inventories handling and other related costs. Furthermore, inaccurate demand forecasting and predictability will necessitate maintenance of buffer stock to safeguard against possible stock out, over and above the threat presented by the inevitable uncertainties of demand and supply since the VCC relies on inventories or components that are crucial for its operations (Colin,2005).
It is important for Frank and William to note that extra stock holding will also culminate to additional costs, hence accurate demand forecasting is crucial. This section therefore presents Frank and William with feasible inventories demand forecasting models and approaches that will enable the company to maintain optimal inventories levels for ultimate SC effectiveness.
Inventories demand forecasting
As a preamble to developing a supply chain that will offer VCC with the highest degree of accuracy and precision in inventories demand forecasting, it is important for the supply chain managers and partners to understand and appreciate that success in the achievement of this objective rests on the level of technological integration in the SC. As such, the various forecasting methods that the company employs must be integrated with state- of- the -art technology (mainly computer- assisted models) so as to fit them with the highest level of accuracy in forecasting inventories demand. This is because such forecasting depends on accurate sales forecasts, the rate of inventories utilization and prediction of inventories availability oscillations/variations.
According to Colin (2005), accurate demand forecasting that is entrenched in intermittent demand forecasting technology present several advantages to the company. First, the latter asserts that accurate inventories demand forecasting assists organization to reduce its inventories levels and the related costs enhances customers’ service via enhancement of customers’ satisfaction through in time meeting of customers needs and promotes overall business control and efficiency in the supply chain management.
Reduction of inventories and inventories cost is usually an imperative objective of supply chain or inventories manager, especially for those businesses which have not achieved a financial footing. Also, most organizations are operating in business environment faced with acutely hard financial times (Rooney & Bangert, 2001). According to the latter, it would be unstrategic for a business which is a financial struggler to hold finances in unnecessary inventories extras.
Accurate demand forecasting therefore will enable Vacumet coating company to maintain optimal levels of inventories making sure that the right amount of component are available where and when they are needed hence avoiding disruptions in the company operations. In the same way reduction of inventories will aid the company in the minimization of inventories carrying costs. For the company (VCC), such accuracy in forecasting is inevitable since its operations solely rely on it i.e. its operations depend on crucial components.
In addition, adoption of technologically assisted inventories demand forecasting techniques will enable VCC not only to reduce the inventories and related costs, but also enhance its capability of meet the growing market demand and exploits the opportunity presented by this increase. In addition, it will help VCC to gain unmatched business control and efficiency that comes with competitive edge over others in the industry.
Ability of the organization in accurately forecasting of inventories demand especially in circumstance where the companies inventories are slow moving will positive transform to business efficiency throughout the other business sector (Collins, 2005). Ideally, the latter will enhance planning other company’s sectors; enhance inventories management, production arrangements and supply planning thus culminating to efficiency and effectiveness in business assets planning and utilization, both in manufacturing finance and other business components in VCC.
Approaches to demand forecasting (models)
Although inventories planners are continuously devising modern models for enhancing accuracy in inventories demand forecasting, there are fundamentally four traditional models that are used to forecast demand. These include quantitative approach, qualitative model, causal regression model, the time series model and simulations (Rooney & Bangert, 2001). However, massive improvements on these models, based on integration of modern technology (computer- assisted software) have been made in an effort to enhance the effectiveness, accuracy and precision of inventories demand forecasting.
For instance, the new inventory demand forecasting technology that was recently developed by smart software, Inc the smart Willemain forecasting method has offered organizations with a technological advancement towards the achievement of organizational wide inventory demand forecasting, planning and inventory optimization capabilities (Collins. 2005). According to Collins (2005), users of this forecasting software have testified having experienced close to 100 percent accuracy in inventories demand forecasting, obtained massive savings in inventories cost and acquired unmatched enhancement of the levels of customers service as well as satisfaction.
Time series
This is a model of inventories demand forecasting that makes use of simple moving averages of inventories for particular periods of time to forecast future inventories needs for the organization. Such averages include, daily, weekly monthly or quarterly averages and which provides fundamental data for the model (Collins, 2005). As such, use of time series to forecast materials demand relies on statistical calculations, hence historical and traditional method of inventory demand forecasting. As noted by Collins (2005) time series relies on historical or rather known data to predict the future or unknown data.
While using time series in forecasting demand therefore, the inventory planners will use past inventory usage data to forecast the future inventory needs for the company. In addition, quantitative models not only support the simulation models to aid variations in time series and increase future demand predictability for the organization, but also offer simple statistical models such as time series to forecast immediate future likely occurrences within the supply chain (Rooney & Bangert, 2001).
Moreover, this model make use of exponential moving averages, trend seasonality regression models, soothing averages and weighted moving averages to forecast inventories demand, thus increasing the level of accuracy and precision in demand forecasting. The time series model has four basic elements which includes seasonality, trends, cycles, and random variations (Collins, 2005).
Simulations
This model of demand forecasting uses consumer demand and consumption patterns, based on consumer choices that culminate to the overall demand so as to forecast future inventories requirements. Although the traditional models that used simulations in forecasting inventories demand were challenging (since they required a lot of data), the introduction and use of varied processes and procedures, coupled with integration of modern technology in the model has greatly lessened the massive data need, hence making it easier to use while retaining its high level of demand forecasting accuracy and precision (Collins, 2005).
As a result, Frank and William can adopt simulations model to enhance the VCC supply chain inventories demand forecasting efficiency but must be sure not only to apply the modern versions of the model but also to integrate state-of- the art technology so as to attain optimal results.
Qualitative models
Qualitative approach utilizes various models which includes but not limited to management judgments, the experts’ opinions, the sales force composite among others based on the previous experience on integration with the market to forecast the firm’s future inventories requirements (Rooney & Bangert, 2001, Collins 2005). Consequently, this model is risky since there is a great likelihood of bias and prejudices, leading to wrong predictions coupled with low accuracy. This is because it relies on no past data hence the outcome of the forecast have little apprehensiveness or believability
Causal regression
In this method of demand forecasting, the independent variables are held with the same weight as the causal variables thus making it subjective (Collins, 2005). While the independent factors are those in control of the organizations, such as production capacity, the causal variable are beyond the control of the organizations such as the SC fluctuations caused by the uncertainty of demand and supply, inevitable inventories shortage and increasing costs as a result of rise in global prices.
Although VCC can use any of the models summarized to forecast its inventories requirements, it is advisable to use simulations or time series/ qualitative models or a combination of both, since they have a higher degree of accuracy, and apprehensiveness compared to causal regression and qualitative models. Furthermore, it is easier and practical to integrate technology in qualitative and simulation models compared to the others which may be impracticable.
The pitfalls of selecting a forecasting method
Fundamentally, there are four main challenges that organizations face in their endeavor to choose an inventory demand forecasting model. First, there are seemingly endless recipe of locations, products and forecasting models that are available for the company.
Secondly, the organizations are often presented with varying time horizons and forecasting methods used for group, financial and replenishment planning. In addition, the supply chain are often faced with a problem of cleansing the historical demands coupled with seasonal profiling that compromises the accuracy of the model since they are left to rely on assumption which may not be authentic. In addition, the forecasting exceptions present a major challenge in the choice of an absolute forecasting model (Cooper et al., 2007).
To overcome these pit falls, it is important for inventories planners to develop a single source of statistical demand forecasting throughout the enterprise, which will provide them with the best trended and adjusted forecast the industry can ever get. In addition, the model chosen must be able to integrate financial planning, variations planning and optimal inventories placements to reduce cost on inventories while ensuring customer’s satisfaction through operations and quality consistency at all times (Collins, 2005, Cooper et al., 2007).
As such, those involved in demand forecasting have to develop in-house demand cleansing approach to avoid being misled by increase in sales as a result of promotions, prices offs, seasonal variations and entry errors that usually come with temporary increase in demand. In addition, the supply chain management must come up with highly efficient and practical ways of resolving forecasting errors which can be achieved by maintenance of high level of flexibility in the supply chain coupled with integration of highly efficient technology.
Wrong forecasting of inventories demand has deathly consequences to the company hence should be avoided by all means. Errors in demand forecasting can either lead to shortages of inventories thus resulting to the company being unable to meet customers need (i.e. fail to meet satisfy the market demand). The ultimate consequences of customers’ dissatisfaction will be; increase in customers’ turnover, loss of business and inability of the company to effectively take advantage of the emerging opportunities as may be presented by market expansion (Jonathan et al., 2007).
In addition, the possible inventories stock outs due to errors in forecasting might lead to paralyses of the firms operations especially if the firm relies on acutely crucial components like Vacumet coating company (VCC). On the other hand, inventories excesses will either lead to wastages through increase in costs especially if the handling costs are high and unnecessary holding of cash on useless inventories which could be more productive if put in other projects. Inefficiency in forecasting or error prone forecasting model will necessitate the organization to maintain large amount of inventories extra/ buffer stock as a means of safeguarding itself against stock outs since the cost on the latter is so high (Rooney & Bangert, 2001).
However, it is almost impracticable to have error free demand forecasting since forecasts are mere predictions of the future and are full of uncertainties (colllins, 2005). To obtain a unit probability or predicting the future with 100% accuracy is not possible, hence forecasts are always wrong. Selection of various approaches to inventories demand forecasting therefore can only serve as a means to lessen the errors of prediction but cannot eliminate it all together. This is due to the fact that some models have a higher degree of accuracy than others.
References
Cooper C et al (2007) Supply Chain Management, More That A New Name For Logistics Inc The International Journal of Logistics Management Vol. 8 pp 1-14.
Colin D. Lewis (2005) Demands Forecasting and Inventory Control: A Computer Aided Learning Approach ISBN: 978-0-471-25338-9.
Jonathan Wright et al (2007) The Sustainable Supply Chain: Balancing Cost, Customer Service and Sustainability to Achieve High Supply Chain Performance. Web.
Rooney C and Bangert, C. (2001), Developing the Right Approach to Requirements Planning under ERP. Web.