Predicting Customer Behavior Research Articles

Predicting E-commerce Sales & Inventory Management using Machine Learning

Due to prevalent transition from visiting physical stores to online shopping, predicting customer behaviour in the e-commerce market is gaining increasing importance. Over the past few years, e-commerce marketplaces such as Flipkart and Amazon have observed a manifold increase in both sales and market share of retail products sold. During this period, many traditional retailers and wholesalers have set up their e-commerce portfolios to stay relevant in the marketplace. However, due to lack of technology penetration in the Medium, Small, & Micro Enterprises (MSMEs) sector, the technological tools required by them are largely absent. One key issue for small businesses in e-commerce has been to forecast how many products their business will sell, thereby introducing another big issue of predicting how much inventory of a product they need to hold, to match up with demand. This is partly due to the massive scale and opportunities opening for them by participating in an open, large marketplace such as e-commerce. The COVID-19 pandemic has also drastically changed consumer shopping trends and behaviours: consumers have changed their preference to buying online. Thus, Indian small businesses need to have the ability to forecast demand more accurately than ever before.

МОДЕЛЬ ПОВЕДІНКИ КЛІЄНТА ЯК ОСНОВА УПРАВЛІННЯ СПОЖИВЧОЮ ЛОЯЛЬНІСТЮ

The aim of the article is to study the features of different models of consumer behavior in order to model their purchasing response and the formation of long-term consumer loyalty to a particular brand. The model of consumer behavior is defined as a description of the relationship between the actions of the consumer of goods and the motives behind these actions, the characteristics of the consumer and the state of the environment in which these actions are carried out. The process of purchasing a product is considered as an action. The study analyzes foreign and domestic models of consumer behavior, approaches to modeling consumer behavior. The motives of product choice, the degree of awareness and independence of choice, the degree of consumer satisfaction with the product, directions and possibilities of influencing consumer choice are studied. Most models of consumer behavior are based on the study of lifestyles of different social strata. Three components of a person's way of life are considered: actions, interests and thoughts. Modeling of consumer behavior is based on the concept of «7 Os»: market participants, their goals; market items; companies present in the market; market operating processes; acquisition opportunities; channels that form methodological approaches to modeling consumer behavior. It has been proven that one of the main factors influencing the purchase decision is consumer loyalty – a system of long-term relationship between supplier and buyer, in which each party refuses to maximize its profits in favor of maintaining this relationship. The greatest contribution to the formation of consumer loyalty have a positive experience of consumption, rational evaluation associations with the brand and the overall strength of all associations with the brand, which sets it apart from alternatives. The formation of consumer loyalty is possible due to the integration into the model of factors of consumer motivation and situational opportunities, taking into account which will achieve greater predictability in predicting customer behavior. The paper proposes an algorithm for consumer loyalty management, which includes the implementation of the following steps: organization of a continuous system of customer service; providing continuous feedback from customers; involvement of customers in regular communication with the brand; creation of a personalized scenario of the client's needs development and formation of a narrowly segmented scenario of his development; encouraging customers to recommend a brand and building a community around the brand among customers who share the business idea. Thus, modeling consumer behavior allows us to understand how, on the one hand, consumers react to the motivating factors of marketing, and on the other – what is a significant competitive advantage for the company.

Model of predicting customer behavior based on big data analysis technologies

The analysis of the available methods and models of formation of recommendations for the potential buyer in network information systems for the purpose of development of effective modules of selection of advertising is executed. The effectiveness of the use of machine learning technologies for the analysis of user preferences based on the processing of data on purchases made by users with a similar profile is substantiated. A model of recommendation formation based on machine learning technology is proposed, its work on test data sets is tested and the adequacy of the RMSE model is assessed. Keywords: behavior prediction; advertising based on similarity; collaborative filtering; matrix factorization; big data; machine learning

An Effective Model for Consumer Need Prediction Using Big Data Analytics

Big data is an unstructured data set with a considerable volume, coming from various sources such as the internet, business organizations, etc., in various formats. Predicting consumer behavior is a core responsibility for most dealers. Market research can show consumer intentions; it can be a big order for a best-designed research project to penetrate the veil, protecting real customer motivations from closer scrutiny. Customer behavior usually focuses on customer data mining, and each model is structured at one stage to answer one query. Customer behavior prediction is a complex and unpredictable challenge. In this paper, advanced mathematical and big data analytical (BDA) methods to predict customer behavior. Predictive behavior analytics can provide modern marketers with multiple insights to optimize efforts in their strategies. This model goes beyond analyzing historical evidence and making the most knowledgeable assumptions about what will happen in the future using mathematical. Because the method is complex, it is quite straightforward for most customers. As a result, most consumer behavior models, so many variables that produce predictions that are usually quite accurate using big data. This paper attempts to develop a model of association rule mining to predict customers’ behavior, improve accuracy, and derive major consumer data patterns. The finding recommended BDA method improves Big data analytics usability in the organization (98.2%), risk management ratio (96.2%), operational cost (97.1%), customer feedback ratio (98.5%), and demand prediction ratio (95.2%).

Clustering Algorithm For Determining Marketing Targets Based Customer Purchase Patterns And Behaviors

Customer segmentation is one of the most important applications in the business world, specifically for marketing analysis, but since the Corona Virus (Covid-19) spread in Indonesia it has had a significant impact on the level of digital shopping activities because people prefer to buy their needs online, so It is very important to predict customer behavior in marketing strategy. In this study, the K-Means Clustering technique is proposed on the RFM (Recency, Frequency, Monetary) model for segmenting potential customers. The proposed model starts from the data cleaning stage, exploratory analysis to understand the data and finally applies K-Means Clustering to the RFM Model which produces three clusters based on the Elbow model. In cluster 0 there are 2,436 customers, in cluster1 1,880 and finally in cluster2 there are 18 customers. RFM analysis can segment customers into homogeneous groups quickly with a minimum set of variables. Good analysis can increase the effectiveness and efficiency of marketing plans, thereby increasing profitability with minimum costs.

The multiple effects of service innovation and quality on transitional and electronic word-of-mouth in predicting customer behaviour

In the service industry, word of mouth (WOM) has become an important indicator for influencing customer behaviour and developing marketing strategies. The current study develops a new theoretical model to analyse the moderating mechanism of electronic WOM, and further considers a multiple mediation analysis of how service innovation may influence in-person word of mouth (WOM) through service quality and brand loyalty. The results show that managers need to focus on WOM to improve customer service quality perception and encourage revisits. A study of 939 customers of a famous hotpot restaurant provides supporting evidence for this moderated mediation analysis. This study also discusses how this intriguing design of moderated mediation could be clarified using regulatory focus theory and further literature.

THE USE OF MACHINE LEARNING TECHNIQUES IN ACCOUNTING. A SHORT SURVEY

Machine learning (ML) is a subset of artificial Intelligence (AI) aiming to develop systems that can learn and continuously improve the abilities through generalization in an autonomous manner. ML is presently all around us, almost every facet of our digital and real life is embedding some ML related content. Customer recommendation systems, customer behavior prediction, fraud detection, speech recognition, image recognition, black & white movies colorization, accounting fraud detection are just some examples of the vast range of applications in which ML is involved. The techniques that this paper investigates are mainly focused on the use of neural networks in accounting and finance research fields. An artificial neural network is modelling the brain ability of learning intricate patterns from the information presented at its inputs using elementary interconnected units, named neurons, grouped in layers and trained by means of a learning algorithm. The performance of the network depends on many factors like the number of layers, the number of each neurons in each layer, the learning algorithm, activation functions, to name just a few of them. Machine learning algorithms have already started to replace humans in jobs that require document’s processing and decision making.

Transforming E-commerce Operations: An Intelligent Business Intelligence Approach for Improving Customer Transaction Management

In the fast-paced world of e-commerce, understanding customer behavior is essential for success. Business intelligence (BI) tools provide valuable insights into customer transactions and can be used to model and predict customer behavior. This paper explores the use of BI techniques for modeling customer transaction behavior in e-commerce. We discuss the various types of BI tools available and their use in analyzing customer data. We then outline a framework for using BI to develop a customer transaction behavior model, including data collection, preprocessing, feature selection, and model selection. Finally, we present a case study in which we apply this framework to a real-world e-commerce dataset and demonstrate the effectiveness of our approach in predicting customer behavior. Our results show that BI techniques can be an effective tool for modeling customer behavior in e-commerce, providing valuable insights for businesses looking to optimize their operations and increase customer satisfaction.

ECONOMIC AND SOCIAL EXCHANGE OF PERSONAL DATA AND THE RISKS OF THEIR PROTECTION

For the economic sector, new technology and communication have become real challenges. Personal data has become an important key to penetrate new markets and several firms are specialized in their collections and sales. Using customer profiles, marketing departments make it easier for them to predict customer behavior and beat competitors. The free movement of goods, payments and data are increasingly common among countries and the protection of personal data is increasingly called into question. Notably, the postmandemic period has significantly increased the distance relationships and data exchange rates. This situation has also contributed to social media addiction. It should be noted that in such a period it is important to increase the level of awareness of Internet users and to be especially careful when issuing data. An important step has been the introduction of a new regulation (GDPR) in the personal data protection system since 2018, which has revised and refined the existing rules and regulations. Especially noteworthy are the Right to be forgetten and the right to data portability.

Perceived Value Dimension, Product Involvement and Purchase Intention for Intangible Cultural Heritage Souvenir

Intangible Cultural Heritage (ICH) souvenir with profound cultural connotation is a new one in China. But there are not much tourists to buy ICH souvenirs. To predict customer behavior, it is necessary to understand the customers’ intention and its antecedents. The study examined the influence of perceived value dimension on purchase intention and the moderating role of product involvement between them. This study conducted an empirical study on ICH souvenir in Suihua city. The findings were that perceived value dimension significantly and positively affected purchase intention for ICH souvenir. By hierarchy regression tests, the findings also showed product involvement played moderating role between perceived value dimension and purchase intention.

Predicting Customer Behavior With Activation Loyalty per Period. From RFM to RFMAP

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.

Predecir el comportamiento del cliente con la lealtad de activación por periodo. Del RFM al RFMAP

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.

Out of sight, out of cancellation: The impact of psychological distance on the cancellation behavior of tourists

Travel products such as package tours, Airtels, hotel rooms, and airline seats lose their value unless they are sold by a certain date. Therefore, predicting customer behavior allows travel companies to maximize their profits, minimize their loss of revenue by balancing supply and demand (e.g., determining an overbooking level), and wisely respond to pressures from the government and customer groups to lessen cancellation penalties. For this reason, it is important to investigate what cause people to cancel their travel plans after reservations have been made. Based on construal level theory (CLT), this study tries to identify the reasons for the cancellation behavior of customers in accordance with different types of psychological distance between travelers and their travel or reservation behavior. Moreover, it examines the moderating role of tourists’ dependence on a travel agency in these relationships for predicting tourist cancellation patterns in a more specific manner.

Leveraging purchase regularity for predicting customer behavior the easy way

The valuation of future customer activity is a mainstay of any organization seeking to efficiently manage its customer portfolio. In the area of customer-base analytics, the ongoing race for predictive power has yielded a large corpus of research to assist managers in this respect. Approaches in the tradition of stochastic models have been particularly successful because they rely only on easy-to-compute key metrics and integrate them within a parsimonious probability-modeling framework. Recent advances in this field have demonstrated that incorporating the timing regularity of past purchases can improve predictive accuracy relative to purely recency/frequency-based approaches. This paper expands that idea and introduces generalizations of a well-established probability model, the BG/NBD (Fader et al., 2005a), by replacing the exponential with a more flexible Erlang-k interarrival timing process. The resulting model variants are capable of leveraging regularity while retaining almost the same level of data requirements and algorithmic efficiency. Using extensive simulation studies and six data sets covering a wide range of empirical settings the authors demonstrate substantial improvements in predictive accuracy against the baseline models and performance gains close to or on par with a more complex model alternative. The availability of efficient and easily accessible implementations of the new model variants in the R-package BTYDplus allows marketing analysts to apply them in large-scale scenarios of data-rich environments on a continuous basis.

A new framework for predicting customer behavior in terms of RFM by considering the temporal aspect based on time series techniques

Data mining and in particular forecasting tools and techniques are being increasingly exploited by businesses to predict customer behavior and to formulate effective marketing programs. Conventionally, customer segmentation approaches are utilized when dealing with a large population of customers. Inspired by this idea, a new methodology is proposed in this study to perform segment-level customer behavior forecasting. To keep the dynamic nature of customer behavior, customer behavior is represented as a time series. Therefore, customer behavior forecasting is changed into a time series forecasting problem. The proposed methodology contains two main components i.e. clustering and forecasting. In the clustering phase, time series are clustered using time series clustering algorithms, and then, in the forecasting phase, the behavior of each segment is predicted via time series forecasting techniques. The main objective is to predict future behavior at segment level. The forecasting component also consists of a combined method exploiting the concept of forecast fusion. The combined method employs a pool of forecasters both from traditional time series forecasting and computational intelligence methods. To test the usefulness of the proposed method, a case study is carried out using the data of customers’ point of sale (POS) in a bank. The results of the experiments demonstrate that the combined method outperforms all other individual forecasters in terms of symmetric mean absolute percentage error (SMAPE). The proposed methodology can be correspondingly applied in other areas and applications of time series forecasting.

O2O서비스품질 특성과 지각된 유용성, Flow경험 및 고객 가치공동창출과의 관계에 대한 연구 : 기술수용모델을 적용

The purpose of this study is to figure out the influence of o2o service quality characteristics on customer value co-creation, and verify the mediating effect of perceived usefulness and flow experience. Specimen are mobile hotel booking application user, aged 18 and above, 59 and below. Survey was started at Oct.03.2019 for 1 month with 350 questionaries, total 310 samples were used for actual analysis. We used IBM SPSS 21.0 program on analysis for demographic quality, used R to perform PLS PM(Partial least squares path modeling) analysis. On H1-2 and H1-3, information quality showed significant effect on perceived usefulness. On H3-2 and H3-3, system quality and service quality showed significant effect on perceived usefulness. On H5-1, perceived usefulness showed significant effect on advocacy. On H6-1 and H6-3, Flow experience showed significant on advocacy and helping. On correlation between perceived usefulness and feedback, old group showed negative effect while young group had positive effect; H5-2 is adopted. On correlation between perceived usefulness and helping, old group showed negative effect while young group had positive effect; H5-3 is adopted. Through this study, few meaningful information to predict customer behavior is found via analyzing patterns of hotel application usage; correlation between o2o service quality characteristics and value co-creation is confirmed, mediating effect and role between perceived usefulness and flow experience is verified.

Customer Behavior Analysis using Weighted Selective Naive Bayesian

The predominant success of each enterprise relies upon the efficient analysis of customer behavior and a deep understanding of customers' needs. Performing better customer analysis provides an effective analysis of potential customers, better decision-making, improved business processes, the measure of customers churn and enhance customer retention. Efficient customer analysis can be performed using the Naive Bayes (NB), which is a simple classifier used for predicting customer behavior. However, the performance prediction of Naive Bayes is strongly affected in some real-time datasets which involve the presence of correlated attributes and this creates a breach of the assumption made by the Naive Bayes model on the dataset. To enhance the performance prediction of the NB and to eliminate correlated variables, this research suggests a simple WSNB (weighted Selective Naive Bayesian) method that uses the C4.5 DT for selecting the attributes with high information values. Then the selected weighted attributes are further used with the Naive Bayes for improving performance prediction. The Experimental approach is tested with a bank client dataset, which indicates that WSNB makes better predictions than the standard Naive Bayes. Also, WSNB reduces the running time of the classifier by eliminating the correlated attributes, which in effect minimize the size of learning and testing data.

The Role of Using Big Data in Predicting Customer Behavior: The Intermediary Role of Business Intelligence in Jordanian Telecommunications Companies (A Field Study).

The Role of Using Big Data in Predicting Customer Behavior: The Intermediary Role of Business Intelligence in Jordanian Telecommunications Companies (A Field Study).

Using machine learning techniques to develop prediction models for detecting unpaid credit card customers

Customer behavior prediction is gaining more importance in the banking sector like in any other sector recently. This study aims to propose a model to predict whether credit card users will pay their debts or not. Using the proposed model, potential unpaid risks can be predicted and necessary actions can be taken in time. For the prediction of customers’ payment status of next months, we use Artificial Neural Network (ANN), Support Vector Machine (SVM), Classification and Regression Tree (CART) and C4.5, which are widely used artificial intelligence and decision tree algorithms. Our dataset includes 10713 customer’s records obtained from a well-known bank in Taiwan. These records consist of customer information such as the amount of credit, gender, education level, marital status, age, past payment records, invoice amount and amount of credit card payments. We apply cross validation and hold-out methods to divide our dataset into two parts as training and test sets. Then we evaluate the algorithms with the proposed performance metrics. We also optimize the parameters of the algorithms to improve the performance of prediction. The results show that the model built with the CART algorithm, one of the decision tree algorithm, provides high accuracy (about 86%) to predict the customers’ payment status for next month. When the algorithm parameters are optimized, classification accuracy and performance are increased.

A Machine Learning Based Method for Customer Behavior Prediction

A Machine Learning Based Method for Customer Behavior Prediction