Entrepreneur Marketing Demand Forecasting - Essay Example

? Entrepreneur Marketing Demand Forecasting Entrepreneur Marketing Demand Forecasting Introduction Forecasting refers to an attempts aimed at predicting overall level of future demand and not specific links, hence there are set of techniques applied in order to forecast demand (Meade & Islam, 2001). In situation where a sales manager has the knowledge concerning the demand, the forecasting techniques are used, while in situation where a manager is seeking to determine the pricing policy of the firm for generating demand increase, estimation techniques are applied. In fact, the paper will discuss techniques applied in marketing demand forecasting. Information concerning the future demand is vital to the firms, for pursuing optimal pricing strategy; hence, the decision to change prices is made considering the future demand. In case where is over-optimism in relation to the estimates of demand, this may result to losses, whereby the demand influence a certain price that sets out at a low level. However, accuracy of information provided creates the likelihood of making decisions that have a positive impact on the firm’s operations and profitability. Decisions made by the managers in a firm are influenced by the level of demand for products, whereby a firm takes non-price factor as a competitive strategy. For instance, the level of advertising in a firm is determined by the perception, which is needed for stimulation of the demand for products (Juster, 2008). Therefore, the level of advertising expenditure depicts the additional cost of the firm that is considered unnecessary spending, hence requiring them to be avoided. There are other cases where the firm expects demand to be low and they seek to compensate expenditure of money that is considered wasted. Instead, they would rather redesign their product in order to respond to the situation, and avoid incurring additional cost in form of expenditure in research and development. APPROACHES FOR SALES FORECASTING Survey-Based: BASES II During the stage one of the Bases II there are intercepts interviews applied, whereby four or more geographically dispersed locations are used as field of studies. The respondents in these interviews are not screened for category usage after presentation of products and services concept to the respondents. In fact, the respondents are asked questions related to the things they like or dislike trial intent as a binary measure, purchase intent as the binary scale, and purchase quality of the product category. The other stage relates to the measure of the after weeks; whereby users are contacted in order to obtain after sue measures that entail measures of repurchase intent. Bases II is used sensibly with discounting factors that are referred to as the top box rule, whereby there are similar categories of products, and there is application of multiple discounting factors. There are elements of pessimism and optimism in sales forecast, and the most difficult part concerning the estimation is the proportion of the awareness that depends on the marketing plan. There are difficulties involved in estimating the relationship between the marketing activities and the level of awareness such as expenditure on advertisements. On the other hand, data is collects in relation to the advertisement expenditure for brands associated with categories of similar products, and this data is made available to the management. Measure of awareness of the brands occurs during the intercept stage; though there is difficulty involved in terms of getting the current rate data. Model-Based Diffusion Model (Bass Model): These models embody a life cycle curve of innovation for new products and services among sets of probable adapters for duration of small number parameters. There are assumptions related to applicable categories of new products, instead of brands, whereby the adapters buy one unit of new product. The other assumption is that the purchases are not repeated, they are applicable to the durable goods and the new products are picked up by the innovators, thereby communicating with the imitators. Diffusion model is applied in situation where there are no data related to historical same, and it is suitable for setting market potential parameters. Moreover, products in the same category have the same bass coefficients, whereby the innovators coefficient is p and is relative to the stable across similar products, while the coefficient of the imitators is q and it varies across products that are the same. Binary Logit Model The model focuses on the choices or trail intent observation for consumer i (i=1,…,I), yi = 0/1 (No/Yes), and the total demand is represented by the formula =?iyi. This makes the key predictor to be yi and an assumption related to Utility Maximization for the consumers. The utility from no purchase decision, whereby utility is offered by the products represented by the function ?’xi+error If ?’xi>0, consumer i willing to purchase the products. The model also entails a survey yi that depicts the product concept, whereby the respondents are asked questions such as if they are likely to buy certain products and the answer are (Yes/No). The independent variables Xi entail an assumption that they are affecting the customers’ decisions. FORECASTING METHODS Delphi This technique was established in 1950s by RAND Corporation in order to facilitate the process of capturing information from to diverse experts, and avoid limitations associated with the conventional group meeting such as bullying and wasting time (Morwitz, 2001). The application of this technique requires a recruitment of twenty experts that are suitable, and they are polled for their forecast and reasons. The experts are offered with anonymous summary of statistics concerning the forecast by the administrators, and the process is repeated up to a point where there is insignificant change in the forecast between the rounds. The process is repeated for two to three rounds and the median or mode of the final forecast is established. Moreover, there is software that is designed to offer guidance through the procedure and this makes the results to more accurate than those derived from unaided judgment and conventional groups (Rowe &Wright, 2001). Unaided judgment This is a technique that involve the common practice of asking the experts opinion on what they expect in the future, and this is considered to be a good idea, which is applicable in situations where the experts are unbiased, and if they understand the relationship substantially. The experts have privileged information, since they acquire accurate and summarized feedback concerning their forecasts. Nevertheless, this technique is in condition that the requirements of the experts are not met such as avoiding biases. Green (2005), explains that experts lack a better chance in situation where they are using unaided judgment to forecast decisions made by people under conditions of conflicts. Prediction markets Prediction markets are also referred using terms such as betting markets, information markets or futures markets have an extensive history. In the period between the closing stages of the Civil War in US and World War II, fine-structured markets for betting on presidential elections accurately chose the victor in all the elections except for 1916. The betting markets were also very effective in pinpointing the elections that would be incredibly competitive (Rhode and Strumpf, 2004).A case in point is the Iowa Electronic Markets which has accomplished better predictions of the margin of victory for the presidential election winner in the four elections preceding the 2004. Of late, internet markets and software are being introduced by some commercial organizations to allow participants to bet by exchanging contracts. Innovationfutures.com is one of the best case of such markets and is now being used to foretell the ratio of US homes with an HDTV in a specific time period (Wolfers & Zitzewitz, 2004). Betting markets are also being set up within organizations to predict on the sales growth of a newly introduced products. It is believed that they can accurately predict the sales in such scenarios. Structured analogies According to Gorr and Szczypula (2001), an analogy is the comparison between two similar things that are similar in some way, often used to help explain something or make it easier to understand. A marketer may forecast the outcome of a new situation, for instance, the behavior of new products in US markets can be used to predict the behavior of similar products other countries on introduction. Although people use analogies, they rarely use them in organized way, they usually search for an analogy that matches their views or they may perhaps end their search when they pinpoint an analogy. For the structured analogies method, one prepares a description of the aimed situation and picks out well-acquainted experts with direct understanding of the situations. The experts are then responsible for searching and pinpointing analogous situations. The experts measure their closeness to the aimed situation, and then accord the results of their analogies with hypothetical results in the aimed situation. From the data, the expert has provided as the closest analogies one can then be able to foretell or forecast a situation. Judgmental Decomposition Judgmental decomposition is because it is easy to foretell a small part of a problem as compared to the whole problem. After dividing the problem into parts one then forecasts the parts individually using suitable methods and lastly merges them together to obtain an overall forecast. A way of carrying out judgmental decomposition is by breaking the problem down into generative components then merging the problem by multiplying the components. It has been observed that forecasts from decomposition are more precise, than an inclusive methodology (MacGregor 2001). In detail, decomposition is more precise in situations where there is much uncertainty about the combined prediction and in cases where numbers used are six-figured or greater. Expert systems In this method, forecasting rules learnt from firsthand research and those used by experts are first identified with the main objective being easiness and wholeness in the ensuing method, which should bring fore the forecasts. Evolving an expert system will only be relevant where many analogous forecasts are required otherwise, it is expensive it is also practicable in a situation where the problems are appropriately finely organized for the rules to be recognized. Collopy, Adya, and Armstrong (2001) did analysis and established that expert systems forecasts are more precise than those from lone judgment although this conclusion was based on only a little number of researches. Conclusion The paper has explored issues related to the forecasting demand by entrepreneurs, thereby the focusing on both the approaches and methods of forecasting. The approaches that can be identified include the survey based approach and the Model-Based and Binary Logit Model. On the other hand, the methods identified include; Delphi, Prediction markets, Judgmental, Decomposition and Expert systems. References Collopy, F, Adya, M. & Armstrong, J. S. (2001). Expert systems for forecasting, in J. S. Armstrong (Ed.) Principles of Forecasting. Norwell, MA: Kluwer Academic Publishers, pp. 285-300 Duncan, G., Gorr, W. & Szczypula, J. (2001). Forecasting analogous time series. In J. S. Armstrong (Ed.) Principles of Forecasting. Norwell, MA: Kluwer Academic Publishers, pp. 195-213 Green, K. C. (2002). Forecasting decisions in conflict situations: A comparison of game theory, role-playing and unaided judgment. International Journal of Forecasting, 18, 321-344. Juster, T. (2008). Consumer buying intentions and purchase probability: An experiment in survey design. Journal of the American Statistical Association. 61, 658-696. MacGregor, D. (2001). Decomposition for judgmental forecasting and estimation. In J. S. Armstrong (Ed.). Principles of Forecasting. Norwell, MA: Kluwer Academic Publishers, pp. 107-123. Meade, N. & Islam, T. (2001). Forecasting the diffusion of innovations: Implications for time series extrapolation,” in J. S. Armstrong (Ed.) Principles of Forecasting. Norwell, MA: Kluwer Academic Publishers, pp. 4577-595. Morwitz, V. (2001). Methods for forecasting from intentions data. In J. S. Armstrong (Ed.) Principles of Forecasting. Norwell, MA: Kluwer Academic Publishers, pp. 33-56. Rowe, G. & Wright, G. (2001). Expert opinions in forecasting role of the Delphi technique. In J. S. Armstrong (Ed.) Principles of Forecasting. Norwell, MA: Kluwer Academic Publishers, pp. 125-144. Rhode, Paul W. & Koleman S. Strumpf (2004). Historical presidential betting markets. Journal of Economic Perspectives. 18 (2): 127-142. Wolfers, J. & Zitzewitz, E. (2004). Prediction markets, Journal of Economic Perspectives, 18 (2), 107-126. Read More