Nowadays, most companies are utilizing customer behavior mining frameworks to improve their business strategies. These frameworks are used to predict different business patterns, such as sales, forecasting, or marketing. Different data mining and machine learning concepts have been
 applied to predict customer behaviors. However, traditional approaches consume more time and fail to predict exact user behaviors. In this paper, intelligent techniques, such as fuzzy clustering and deep learning approaches, are utilized to investigate customer portfolios to detect customers’
 purchasing patterns. To accomplish this objective, hierarchical fuzzy clustering was applied to compute the relationship between products and purchasing criteria. According to the analysis, similar data are grouped together, which reduces the maximum error classification problem. Then, an
 optimized deep recurrent neural network is incorporated into this process to improve the prediction rate. The discussed system efficiency is evaluated using a number of datasets with respective performance metrics. The proposed approach was compared to other single model-based and hybrid model-based
 approaches and was found to attain maximum accuracy and minimum error rate in comparison.

Behavior Prediction Scheme Using Hierarchical Clustering and Deep Neural Networks

Data-driven decision making is increasingly becoming an essential component of marketing practice across all business sectors and receives unprecedented attention in terms of policies and financial support. The purpose of this article is to improve our understanding of data-driven decision-making strategies and focus on a comprehensive view of applications in marketing and related research. As such, we intend to establish a perspective on strategic planning and management of data-based marketing, complementing the understanding through the current literature. By adopting the "data-driven" perspective, marketers benefit from an approach of more and better control over data and a broader knowledge of the organization's data and strategic models in order to obtain relevant decisions.

Data-driven decision making strategies applied to marketing

Compared with the past questionnaire survey, this paper applies the intelligent algorithm developed rapidly in recent years to identify the tendency of customers to buy financial products in the market. In addition, for the single state customer classification indicators based on the previous demographic information and action information, it is proposed to combine the action of market activities with demographic information; that is, the static integrated customer classification index is further combined with the improved neural network model to study the classification and preference of enterprise financial customers. Firstly, the enterprise financial customer classification model based on neural network algorithm is studied. Aiming at the shortcomings of easy falling into the local optimal solution of neural network algorithm, slow convergence speed of algorithm, and difficult setting of network structure, combined with the characteristics of genetic algorithm, the concept of adaptive genetic neural network algorithm is proposed. Then, the design of adaptive genetic neural network model is studied. Secondly, combined with the customer data of a financial enterprise and the characteristics of enterprise finance, this paper analyzes the risk influencing factors of enterprise financial customers, analyzes the customer data, evaluates the enterprise financial customers through the adaptive genetic neural network model, and realizes the classification of enterprise financial customers. Through an example, it is proved that the enterprise financial customer classification and preference model based on the adaptive genetic neural network algorithm discussed in this paper has better customer classification accuracy and can provide better method support for enterprise financial customer management.

Research on Enterprise Financial Customer Classification Method and Preference Based on Intelligent Algorithm

We applied data mining techniques to analyze customer behavior for an online Saudi store using historical purchase data. Unsupervised learning was used to segment customer behaviors using the following clustering algorithms: k-means clustering, hierarchical clustering,and DBSCAN. Clustering results were compared on the basis of the Silhouette score, Davies-Bouldin index, and Calinsk-Harabasz index. The results revealed that k-means clustering with $\mathrm{k}=5$ produced the most logical clusters. The clustering techniques managed to segregate customers into different segments according to total payments and the number of purchases they made. The clusters showed slight differences in customer spending habits. This approach had potential merit for the online store, as it makes it easy to target marketing for each category, such as presenting discount coupons, introducing new products and services, and making changes to existing services according to customer requirements.

Application of Unsupervised Learning and Data Clustering to Saudi Online Stores

Firms need to integrate multiple business functions in order to acquire, analyze, model, and evaluate information necessary for better understanding customer behaviors and making data-driven decisions to enhance the customer experience journey. This study proposes a customer oriented intelligent decision support system (IDSS) to ultimately improve the customer experience journey. Besides, a real application study is handled for a multinational company located in Turkey, considering its abrasives product sales for years of 2017 and 2018. For the data utilized in application study, the proposed methodology is constructed for customer segmentation to develop appropriate data-driven marketing strategies for customers with similar values, preferences and other factors for creating customer-centric organizations. In this regard; firstly two-phased clustering process, which involves the hierarchical multivariate average linkage clustering algorithm and partitional k-means clustering algorithm, is used to present the number of clusters on the basis of three variables (expenditure, transaction and unit cost) and then to assign the customers to the related clusters (VIP, Platinum, Gold and Bronze), respectively. Secondly, the performances of company’s departments are ranked according to the preferences of customers from each segment considering 4Ps marketing mix concept via integrated methodology of interval type-2 Fuzzy AHP and hesitant fuzzy TOPSIS.

Customer oriented intelligent DSS based on two-phased clustering and integrated interval type-2 fuzzy AHP and hesitant fuzzy TOPSIS

Customer segmentation is the process of dividing customers into groups based on common similar characteristics such as value, location, demography etc. Companies can communicate with each group effectively and appropriately by considering these common properties. Data mining algorithms are the most utilized techniques which lead direct marketers to develop their marketing strategies tailored to particular segments and/or individuals. Clustering is one of the unsupervised data mining methods used for grouping set of objects such a way that objects in the same group have maximum similarity while between group similarities are low. K-means clustering is a commonly used non-hierarchical clustering method for performing non-parametrical learning tasks. This study aims to identify customer types according to their profitability, value and risk in order to take appropriate action for each group via clustering. In this study, data items are grouped according to coded customer profile with respect to the consumers’ total expenditures. Customers are segmented as VIP, Platinum, Gold, and Bronze into 4 groups according to their values within 2 years.

Necla Yel

Papers

Customer oriented intelligent DSS based on two-phased clustering and integrated interval type-2 fuzzy AHP and hesitant fuzzy TOPSIS

An Unsupervised Data Mining Approach for Clustering Customers of Abrasive Manufacturer