Predicting customer behavior with Activation Loyalty per Period. From RFM to RFMAP

Abstract

Objective:Identify a new model of predicting customer behavior based on new variables that can be used by marketing management and adapted to their business planning. Methodology: New model has been used, with the definition of new calculation systems of the traditional variables R, Recency, F, Frequency, and M, monetary value, (RFM), related to the business periods. Besides, activation in each period P becomes a key variable for constructing the purchase cohorts of customers and identifying their potential. A new variable, Activation Loyalty, is recognized as a good proxy of the likelihood of future customer purchases. The model builds a weighting through a multiple regression analysis obtaining β for each variable, including the periods of activation, presenting the relative effect of the variables, and the best global explanation of the model. Results: This new model, RFMAP, which includes Activation Periods and Activation Loyalty, presents a higher prediction accuracy and improvements over traditional models with a clear impact, useful and manageable lines of segmentation, and prioritization for marketing management in CRM systems. Limitations: The main limitation of this model consists that it is based on data of only one company, and it should show the value in other sectors and give a full insight through its transversal application. Practical implications: The involved advantages demonstrated better predictability and usefulness to decision-makers, not only to determine the best customers but also with lapsed ones. It gives a meaningful explanation of differences in customer behavior, which are present in the data and are being reflected in the model. Also, it provides a prescriptive prioritization of variables to be managed in the marketing plan and how to be implemented.

Behavior Analysis Using Enhanced Fuzzy Clustering and Deep Learning

“…The variable in the network has an energy model with a separate state, which is more useful in forming the cluster. The visible and hidden nodes' energy state levels are estimated using Equation (7).…”

“…In Equation (7), the model parameter is defined as θ ={w, a, b}, the weight between i (visible unit) and j (hidden unit) is denoted as w i,j , and biases are represented as a i and b j . The computed state value helps assign the probability value to every visible and hidden vector pair.…”

“…The variable in the network has an energy model with a separate state, which is more useful in forming the cluster. The visible and hidden nodes' energy state levels are estimated using Equation (7). v,h,θ)=-∑ a i v i -∑ b j h j -∑ v i h j w i,j i,j j∈hidden i∈visible (7) In Equation (7), the model parameter is defined as θ={w,a,b}, the weight between i (visible unit) and j (hidden unit) is denoted as w i,j , and biases are represented as a i and b j .…”

“…A large volume of data are needed for the training procedure; therefore, big data techniques have been incorporated into BI to increase identification accuracy and to understand customer preferences. Various businesses are interested in creating automated BI systems by integrating big data and machine learning techniques [6,7]. This approach minimizes computational complexity and improves the overall prediction rate.…”

RFID: A Fuzzy Linguistic Model to Manage Customers from the Perspective of Their Interactions with the Contact Center

“…Case study of a retail business [40]; Genomics-first evaluation of heart disease associated with titin-truncating variants [41]; Marketing strategies evaluation based on big data analysis: a CLUSTERING-MCDM approach [42]; Predicting customer behavior with activation loyalty per period. From RFM to RFMAP [43]; A review of the application of RFM model [5]; Predicting customer value per product: From RFM to RFM/P [44]; RFM-based repurchase behavior for customer classification and segmentation [45]; Customer stratification theory and value evaluation-analysis based on improved RFM model [46].…”