روش کمی استخراج ضریب همبستگی برای هوش کسب و کار(هوش تجاری) در شرکت های کوچک و متوسط ​​کسب و کار تجاری

Business intelligence based on data mining has been one of the popular and indispensable tools for identifying business opportunity in sales and marketing of new products. The traditional data mining methods based on association rules may be inadequate in completely uncovering the hidden patterns of sales based on transaction records. This paper presents a qualitative correlation coefficient mining method which is capable of uncovering hidden patterns of sales and market. Hence, a prototype business intelligence system (BIS) named correlation coefficient sales data mining system (CCSDMS) has been developed and successfully trial implemented in a selected reference site. A series of experiments have been conducted to evaluate the performance of the proposed system. The results generated by the BIS are compared with a well known market available data mining system. The proposed quantitative correlation coefficient mining method is found to possess higher accuracy, better computational effectiveness and higher predictive power. With the new approach, associations for product relations and customer periodic demands are revealed and this can help to leverage organizational marketing capital to enhance quality and speed of promotions as well as awareness of product relations.

Conventionally, companies desire to know what customers need and where companies should focus on the market in order to survive in today’s highly competitive market. The management of market inquiries and customer relationships in organizations pay great attention to the strengthening of their organizational development. Vindevogel, Van Den Poel, and Wets (2005) studied the market basket analysis as the base for the promotion strategy for products. Buckinx, Verstraeten, and Van Den Poel (2007) make use of the internal transactional database for predicting customer loyalty for targeted marketing actions while Larivière and Van Den Poel (2005) attempt to better understand important measures of customer outcome such as next buy, partial defection and customers’ profitability evolution by using random forest and regression forest techniques. Jonker, Piersma, and Van Den Poel (2004) present a joint optimization approach for the segmentation of customers and the development of the optimal policy towards homogeneous groups of customers. Burez and Van Den Poel (2007) make use of different churn-prediction models for early detection of potential churners which enables an European pay-TV company to target their customers using specific retention actions, and subsequently increase profits. The concept of a business intelligence (BI) system is adopted in various industries in order to meet their specific business requirements. Miller, Dagmar, and Stefanie (2006) defined BI is getting the right information to the right people at the right time. BI constitutes a broad category of applications and technologies for gathering, storing, analyzing, and providing access to data to help people in the organization to make better business decisions.

To satisfy customer needs in nowadays competitive market, data mining is an effective approach to be adopted in companies. This paper presents a quantitative correlation coefficient mining algorithm for revealing sales patterns and its various applications in a company. A prototype business intelligence (BI) system has been built which is composed of a Data Preparation Phase (DPP) and Sales Alerting and Analysis System (SAAS), respectively. Product relation network visualization and analysis is also undertaken to uncover hidden patterns of sales and market. The CCSDMS is successfully trial implemented in a selected reference site named Angus Electronics Co. A series of experiments have also been conducted to evaluate the performance of the proposed systems. The results generated by CCSDMS are compared with that of Weka. Encouraging results are obtained for the performance evaluation and the system performance of the proposed systems is found to be superior than that of commercial available BI system. After adopting these applications, company can recognize the actual product ordering patterns and customer ordering behaviors. The results give great impact to the company since unexpected and potential marketing information is obtained. Then speedy and proper responds can be done to fulfill market demands. For further development of this research work, it is suggested to deduce associations between different customers by analyzing consuming patterns. At present, different parties of customers can be classified in a market. Qualities and supports of organizational sales strategies can be further enhanced.