Özet:

The estimated amount of sales affects many divisions in, from the purchase of raw materials to the determination of advertising costs. A large number of consumer data is needed to be used in sales forecasts. The use of many consumer data is a problem because it is personal. Nevertheless, the data from social networks and search engines that are effective in the purchase decision process is open to access by everyone, in addition to being valuable. It is important for to estimate sales figures close to reality and for consumers to protect personal data. In this context, the study aims to estimate the sales amount of a car brand using the online consumer integration and search engine data that are effective and public in the consumer’s decision-making process. 2267 posts created between 2012 and 2017 from the Facebook brand page of the company, where the Online Consumer Integration is intense, and the likes, comments and sharing data of these posts have been collected with the Facebook Graph API. Search engine data is obtained from Google Trends, sales data from the Automotive Distributors Association’s website. The data was normalized by the Min-Max method and analyzed by the artificial nerve networks, by the Bayesian Regulation method of re-semination. Facebook’s brand page and search engine data have estimated a successful sales amount with a correlation of 74% and an average error value of 1%. In addition, the detailed data covered 6 years is presented as identifying information.  In the study, successful sales forecasts were made without the use of consumer’s specific information. However, the study is based on real data and contributes to the industry and academic literature through the use of artificial nerve networks in the business field.

Özet:

Estimation of sales volume affects many segments of the enterprises from raw material purchase to advertising expenses. A large number of consumer data is needed to be used in sales forecasting. The use of many consumer data is private, causing problems. On the other hand, data from social networks and search engines, which are influential in the purchasing decision process, are valuable and accessible to everyone. For businesses, it is important to estimate sales figures accurately. For consumers, protecting their personal data is substantial. In this study, it is aimed to estimate the sales volume of an automobile brand by using Online Consumer Engagement and search engine data which are effective in the purchasing decision process of consumers and publicly available. 2267 posts, created between 2012-2017, likes, comments, and sharing data of these posts were taken from Facebook brand page of the business where Online Consumer Engagement is intense using Facebook Graph API. Search engine data was obtained from Google Trends, and sales data was obtained from Automotive Distributors Association website. Data were normalized by Min-Max method and analyzed by feedforward artificial neural networks and Bayesian Regulation backpropagation method. Successful sales volume estimation, whose the correlation value is %74 and mean error value is %1, was made with Facebook brand page and search engine data. In addition, detailed data covering 6 years has been prepared and presented as descriptive information. In the study, successful sales estimation was made without using the private information of the consumers. This study contributes to the sector and academic literature by relying on real data and using artificial neural networks in the business administration.

Anahtar Kelimeler: