In the modern business era, identifying and understanding various customer segments is key to success. Building strong relationships with customers can ensure the sustainability of revenue sources for businesses. One way to gain an in-depth understanding of customers is to segment them and study the unique characteristics of each group. In today’s competitive market, where customers have many choices, analyzing customer behavior and applying the right marketing strategies are crucial factors in determining a company’s success.
A deep understanding of customer behavior is a crucial aspect of customer relationship management (CRM). With the rapid development of information technology, data collected from various business activities requires more sophisticated analysis to gain accurate insights into customer behavior and purchasing patterns. This is essential for adopting the right marketing strategies and meeting customer needs. Therefore, analytical tools and data mining are important prerequisites in adopting effective CRM approaches.
One essential data mining technique is customer segmentation. Data mining helps companies identify and track customer behavior and patterns during their interactions with the company. This leads to improved customer service, increased sales, more effective distribution, and better marketing strategies. Innovations in data mining are highly needed to support decision-makers in the agricultural industry. Previous research has shown that effective production and sales strategies for agricultural products require proper customer segmentation. The main contribution of this research is to introduce a big data analysis method for segmenting customers based on age and developing appropriate strategies for each group.
This article also discusses the segmentation of business-to-business (B2B) customers using the Recency, Frequency, Monetary (RFM) model. This research uses the RFM model and the k-means algorithm to segment customers and uses the Davies–Bouldin index to evaluate the quality of the formed segments. This study segments 12 main customer groups from a food company, each representing different consumer markets (e.g., hospitals, universities, municipalities). The results show that segmenting customers into three clusters can increase their purchase value and customer loyalty.
Industrialization increases the volume of capital in the agricultural industry and helps modernize the sector, ultimately increasing production. The relationship between the agricultural sector and services, particularly transportation and communication, is very close. These two sectors play an important role in maintaining agricultural products amid technological changes and the growth of global trade.
An important managerial application of this research is the improvement strategy in the agricultural industry. The applied machine learning approach can identify several effective strategies that can be applied to various challenges in the agricultural industry. For example, this approach can be used to optimize the supply of industrial equipment and improve agricultural growth and development.
However, this research has several limitations, including a high dependence on the quality of input data. The lack of necessary data availability can hinder the achievement of desired results. To refine this research, it is recommended to focus on optimizing customer segmentation and using new meta-heuristic algorithms such as the Grey Wolf Optimizer and Ant Lion Optimization.
By applying data mining methods in agricultural customer segmentation, businesses can better understand the needs and preferences of customers, thus designing more effective marketing strategies and increasing customer satisfaction and loyalty.