Customer Lifetime Value Prediction Research Articles

Correction to: A high-performance turnkey system for customer lifetime value prediction in retail brands

Correction to: A high-performance turnkey system for customer lifetime value prediction in retail brands

A high-performance turnkey system for customer lifetime value prediction in retail brands

Customer lifetime value (CLV) modeling underpins modern marketing analytics, enabling the development of tailored customer relationship management strategies based on the predicted future value of their customers. As part of Amperity’s enterprise customer data platform (CDP), we deploy and maintain a CLV prediction system that caters to a rapidly growing list of brands across various industries, purchase behaviors, and scales. Given the impracticality of developing bespoke models for each brand, our solution must be adaptive, generalizable, and high-performing ”out of the box”. Furthermore, our platform demands daily prediction updates to facilitate prompt marketing decisions. This paper introduces a turnkey CLV prediction system that achieves state-of-the-art performance across a diverse set of brands. This system has several contributions: 1) the use of encodings and embeddings to incorporate signals from high-cardinality data; 2) a multi-stage churn-CLV modeling framework that augments additional flexibility in adjusting churn probabilities, subsequently reducing CLV prediction errors while maintaining a synergistic learning process; 3) a feature-weighted ensemble of both generative and discriminative models to accommodate diverse underlying purchase patterns. Empirical results show that our enhanced model consistently surpasses benchmark performances for twelve retail brands across six evaluation intervals from June 2020 to September 2022.

A meta-learning based stacked regression approach for customer lifetime value prediction

Companies across the globe are keen on targeting potential high-value customers in an attempt to expand revenue, and this could be achieved only by understanding the customers more. Customer lifetime value (CLV) is the total monetary value of transactions or purchases made by a customer with the business over an intended period of time and is used as a means to estimate future customer interactions. CLV finds application in a number of distinct business domains, such as banking, insurance, online entertainment, gaming, and e-commerce. The existing distribution-based and basic (recency, frequency, and monetary)-based models face limitations in terms of handling a wide variety of input features. Moreover, the more advanced deep learning approaches could be superfluous and add an undesirable element of complexity in certain application areas. We, therefore, propose a system that is able to qualify as both effective and comprehensive, yet simple and interpretable. With that in mind, we develop a meta-learning-based stacked regression model that combines the predictions from bagging and boosting models that are found to perform well individually. Empirical tests have been carried out on an openly available online retail dataset to evaluate various models and show the efficacy of the proposed approach.

A novel approach to predicting customer lifetime value in B2B SaaS companies

AbstractIn this paper, we propose a flexible machine learning framework to predict customer lifetime value (CLV) in the Business-to-Business (B2B) Software-as-a-Service (SaaS) setting. The substantive and modeling challenges that surface in this context relate to more nuanced customer relationships, highly heterogeneous populations, multiple product offerings, and temporal data constraints. To tackle these issues, we treat the CLV estimation as a lump sum prediction problem across multiple products and develop a hierarchical ensembled CLV model. Lump sum prediction enables the use of a wide range of supervised machine learning techniques, which provide additional flexibility, richer features and exhibit an improvement over more conventional forecasting methods. The hierarchical approach is well suited to constrained temporal data and a customer segment model ensembling strategy is introduced as a hyperparameter model-tuning step. The proposed model framework is implemented on data from a B2B SaaS company and empirical results demonstrate its advantages in tackling a practical CLV prediction problem over simpler heuristics and traditional CLV approaches. Finally, several business applications are described where CLV predictions are employed to optimize marketing spend, ROI, and drive critical managerial insights in this context.

PerCLTV: A General System for Personalized Customer Lifetime Value Prediction in Online Games

Online games make up the largest segment of the booming global game market in terms of revenue as well as players. Unlike games that sell games at one time for profit, online games make money from in-game purchases by a large number of engaged players. Therefore, Customer Lifetime Value (CLTV) is particularly vital for game companies to improve marketing decisions and increase game revenues. Nowadays, as virtual game worlds are becoming increasingly innovative, complex, and diverse, the CLTV of massive players is highly personalized. That is, different players may have very different patterns of CLTV, especially on churn and payment. However, current solutions are inadequate in terms of personalization and thus limit predictive performance. First, most methods just attempt to address either task of CLTV, i.e., churn or payment, and only consider the personalization from one of them. Second, the correlation between churn and payment has not received enough attention and its personalization has not been fully explored yet. Last, most solutions around this line are conducted based on historical data where the evaluation is not convincing enough without real-world tests. To tackle these problems, we propose a general system to predict personalized customer lifetime value in online games, named perCLTV. To be specific, we revisit the personalized CLTV prediction problem from the two sub-tasks of churn prediction and payment prediction in a sequential gated multi-task learning fashion. On this basis, we develop a generalized framework to model CLTV across games in distinct genres by heterogeneous player behavior data, including individual behavior sequential data and social behavior graph data. Comprehensive experiments on three real-world datasets validate the effectiveness and rationality of perCLTV, which significantly outperforms other baseline methods. Our work has been implemented and deployed in many online games released from NetEase Games. Online A/B testing in production shows that perCLTV achieves a prominent improvement in two precision marketing applications of popup recommendation and churn intervention.

FORECASTING CUSTOMER FUTURE BEHAVIOR IN RETAIL BUSINESS USING MACHINE LEARNING MODELS

The ability to forecast customers’ future purchases, lifetime value, and churn are fundamental tasks in business management. These tasks become more complicated when the relationship between customers and business is not contractual. Therefore, the application of an appropriate method of customer analysis influences the efficiency of company cost management in interaction with their customers. The purpose of this paper is to compare existing solutions of customer lifetime value prediction and provide a new way to predict the future behavior of customers with consideration of the drawbacks of previous works. The method should have the following properties: use data that is available in any retail business; take into account that markets are constantly changing; be more precise than existing solutions. In this paper, we proposed the method of identifying customer churn provided a way to analyze customer behavior associated with churn or retention. In order to understand why customers churn, we used eleven customer behavioral metrics. The relationship of used metrics with churn was proved using churn cohort analysis. The results of training of logistic regression and neural network on prepared dataset showed that their forecast accuracy is in the healthy range for highly predictable churn. Based on predicted churn probabilities, we calculated the customer lifetime value in the future period. Our research results on customer behavior in the retail business confirm the hypothesis that customers who make many purchases are less likely to churn than customers who make few purchases. The main uniqueness of this work is the way of finding customer churn, as no such data was provided in the initial dataset. In addition, the minimum amount of data that most retail companies have was used. This enables the proposed methodologies to be applied to a large number of retail companies.

Architecture for Evaluating Customer Retention Strategies

The modernizing world with increasing technological developments and the everyday generation of the new innovative strategies has created a competitive era. The advancement of technology, implementation of advanced solutions, and strategies attract many customers, which results in changing market and business. With this Digital Darwinism, organizations face a major pitfall known as Customer Attrition. Addressing this problem is the need of the hour for every organization aiming to increase customer loyalty and its revenue. Understanding the business ecosystem and coming up with a strategy that strengthens the roots of the firm and increasing their customer lifetime is an approach, but the question arises that how good is your strategy when it comes to the comparison with the competitors in the market. The architecture proposed in this paper evaluates business strategy using customer segmentation and customer lifetime value prediction, churn prediction, uplift modelling, and survival analysis.

Customer lifetime value prediction for gaming industry: fuzzy clustering based approach

The use of fuzzy logic in machine learning is becoming widespread. In machine learning problems, the data, which have different characteristics, are trained and predicted together. Training the model consisting of data with different characteristics can increase the rate of error in prediction. In this study, we suggest a new approach to assembling prediction with fuzzy clustering. Our approach aims to cluster the data according to their fuzzy membership value and model it with similar characteristics. This approach allows for efficient clustering of objects with more than one cluster characteristic. On the other hand, our approach will enable us to combine boosting type ensemble algorithms, which are various forms of assemblies that are widely used in machine learning due to their excellent success in the literature. We used a mobile game’s customers’ marketing and gameplay data for predicting their customer lifetime value for testing our approach. Customer lifetime value prediction for users is crucial for determining the marketing cost cap for companies. The findings reveal that using a fuzzy method to ensemble the algorithms outperforms implementing the algorithms individually.

Profitable Retail Customer Identification Based on a Combined Prediction Strategy of Customer Lifetime Value

As a fundamental concept of customer relationship management, customer lifetime value (CLV) serves as a crucial metric to identify profitable retail customers. Various methods are available to predict CLV in different contexts. With the development of consumer big data, modern statistics and machine learning algorithms have been gradually adopted in CLV modeling. We introduce two machine learning algorithms—the gradient boosting decision tree (GBDT) and the random forest (RF)—in retail customer CLV modeling and compare their predictive performance with two classical models—the Pareto/NBD (HB) and the Pareto/GGG. To ensure CLV prediction and customer identification robustness, we combined the predictions of the four models to determine which customers are the most—or least—profitable. Using 43 weeks of customer transaction data from a large retailer in China, we predicted customer value in the future 20 weeks. The results show that the predictive performance of GBDT and RF is generally better than that of the Pareto/NBD (HB) and Pareto/GGG models. Because the predictions are not entirely consistent, we combine them to identify profitable and unprofitable customers.

Improved Customer Lifetime Value Prediction With Sequence-To-Sequence Learning and Feature-Based Models

The prediction of the Customer Lifetime Value (CLV) is an important asset for tool-supported marketing by customer relationship managers. Since standard methods based on purchase recency, frequency, and past profit and revenue statistics often have limited predictive power, advanced machine learning (ML) techniques were applied to this task in recent years. However, existing approaches are often not fully capable of modeling certain temporal patterns that can be commonly found in practice, such as periodic purchasing behavior of customers. To address these shortcomings, we propose a novel method for CLV prediction based on a combination of several ML techniques. At its core, our method consists of a tailored deep learning approach based on encoder–decoder sequence-to-sequence recurrent neural networks with augmented temporal convolutions. This model is then combined with gradient boosting machines (GBMs) and a set of novel features in a hybrid framework. Empirical evaluations based on real-world data from a larger e-commerce company and a public dataset from the domain of online retail show that already the sequence-based model leads to competitive performance results. Stacking it with the GBM model is synergistic and further improves accuracy, indicating that the two models capture different patterns in the data.

Customer Lifetime Value Prediction: A Study on Multiple Brands Purchase of Consumer Packaged Goods

Customer Lifetime Value Prediction: A Study on Multiple Brands Purchase of Consumer Packaged Goods

RFID-based intelligent shopping environment: a comprehensive evaluation framework with neural computing approach

This research proposes a radio frequency identification (RFID)-based intelligent shopping environment and its distributed reading capability to raise quality of service through improving the automation of product presentation, inventory monitor, billing procedures, manpower logistics, and customer lifetime value prediction. This research also uses RFID to successfully create a smart-shelf-enabled system as an advanced decision-making mechanism for managers. A case study based on a well-known fashion retailing company is used to demonstrate how the proposed system can significantly improve daily business operations. In addition, this research also used artificial neural network to predict the VIP member classification and customer retention rate. The experimental results figure out that the artificial intelligence approach would be outperformed the statistical and decision tree methods. Finally, a questionnaire was administered to 120 customers and investigated their degree of RFID usage willingness and purchase intention based on the Unified Theory of Acceptance and Use of Technology model. The empirical results of our study present the easy-to-use and social influence factors that would be most influenced the customers' usage willing and purchase intention with RFID technology.

A comparative study of hybrid machine learning techniques for customer lifetime value prediction

PurposeCustomer lifetime value (CLV) has received increasing attention in database marketing. Enterprises can retain valuable customers by the correct prediction of valuable customers. In the literature, many data mining and machine learning techniques have been applied to develop CLV models. Specifically, hybrid techniques have shown their superiorities over single techniques. However, it is unknown which hybrid model can perform the best in customer value prediction. Therefore, the purpose of this paper is to compares two types of commonly‐used hybrid models by classification+classification and clustering+classification hybrid approaches, respectively, in terms of customer value prediction.Design/methodology/approachTo construct a hybrid model, multiple techniques are usually combined in a two‐stage manner, in which the first stage is based on either clustering or classification techniques, which can be used to pre‐process the data. Then, the output of the first stage (i.e. the processed data) is used to construct the second stage classifier as the prediction model. Specifically, decision trees, logistic regression, and neural networks are used as the classification techniques and k‐means and self‐organizing maps for the clustering techniques to construct six different hybrid models.FindingsThe experimental results over a real case dataset show that the classification+classification hybrid approach performs the best. In particular, combining two‐stage of decision trees provides the highest rate of accuracy (99.73 percent) and lowest rate of Type I/II errors (0.22 percent/0.43 percent).Originality/valueThe contribution of this paper is to demonstrate that hybrid machine learning techniques perform better than single ones. In addition, this paper allows us to find out which hybrid technique performs best in terms of CLV prediction.

Dynamic customer lifetime value prediction using longitudinal data: An improved multiple kernel SVR approach

Customer lifetime value (CLV), as an important metric in customer relationship management (CRM), has attracted widespread attention over the last decade. Most CLV prediction models do not take into consideration the dynamics of the customer purchase behavior and changes of the marketing environment such as the adoption of different promotion policies. In this study, a framework for the dynamic CLV prediction using longitudinal data is presented. In the framework, both the dynamic customer purchase behavior and customized promotions are considered. An improved multiple kernel support vector regression (MK-SVR) approach is developed to predict the future CLV and select the best promotion using both the customer behavioral variables and controlled variable about multiple promotions. Computational experiments using two databases show that the MK-SVR exhibits good prediction performance and the usage of longitudinal data in the MK-SVR facilitate the dynamic prediction and promotion optimization.

Using downside CAPM theory to improve customer lifetime value prediction in non-contractual setting

Identifying and selecting the most profitable customers from a shareholder’s perspective is of great interest to marketing managers. One promising line in this regard is to explore the customer lifetime value and its profitable management over time. There is a significant body of marketing literature about CLV evaluation in terms of various perspectives. However, much less attention has been paid to the risk associated with customer relationships. Previous researches in this area considered risk as “variability of cash flows generated by customers”, regardless of the trend of variability. Whereas the upside and downside variability from the customer’s expected profitability are extremely different in CRM context. This paper provides a quantitative model based on downside Capital Asset Pricing Model (D-CAPM) to evaluate riskadjusted CLV and compares the results by employment of traditional CAPM. This paper contributes to this field by extending the discussion on customer risk measurement and provides an approach that enables marketing managers to evaluate the risk of decline from average profitability for different customer segments.

Customer lifetime value prediction by a Markov chain based data mining model: Application to an auto repair and maintenance company in Taiwan

The present study attempts to establish a framework for computing customer lifetime values for a company in the auto repair and maintenance industry. The customer lifetime value defined in this study consists of the current and future values of a customer, which involve an estimation of lifetime length, future purchasing behavior and the profit associated with each behavior of the customer. The proposed framework contains three groups of techniques to obtain these estimates from historical customer transactions. The first group includes a logistic regression model and a decision tree model to estimate the churn probability of a customer and to, further, predict the lifetime length of the customer. The second group comprises a regression analysis to identify the critical variables that affect a customer’s purchasing behavior, and a Markov chain to model the transition probabilities of behavior change. Finally, the third group contains two neural networks to predict the profits contributed by a customer under various purchasing behaviors. The proposed framework is demonstrated with the historical customer transactions of an auto repair and maintenance company in Taiwan.