Lifetime Value Research Articles

Assessing the Predictive Performance of Machine Learning in Direct Marketing Response

This paper intends to better understand the pre-exercise of modeling for direct marketing response prediction and assess the predictive performance of machine learning. For this, the authors are using a machine learning technique in a dataset of direct marketing, which is available at IBM Watson Analytics in the IBM community. In the results, first, among all variables, customer lifetime value, coverage, employment status, income, marital status, monthly premium auto, months since last claim, months since policy inception, renew offer type, and the total claim amount is shown to influence direct marketing response. However, others have no significance. Second, for the full model, the accuracy rate is 0.864, which implies that the error rate is 0.136. Among the patients who predicted not having a direct marketing response, the accuracy that would not have a direct marketing response was 87.23%, and the accuracy that had a direct marketing response was 66.34% among the patients predicted to have a direct marketing response.

Maximizing Online Revisiting and Purchasing: A Clickstream-Based Approach to Enhancing Customer Lifetime Value

ABSTRACT Online retailers are increasingly focused on maintaining a long-term relationship with customers, encouraging repeat visits rather than single-time purchases to increase customer lifetime value. To help retailers maximize the probabilities of customers’ revisiting and purchasing, we develop a two-stage model to better characterize and predict these two fundamental customer activities. In the first stage, we characterize the propensity of a customer revisiting the retailer’s website. In the second stage, we develop a stochastic model that predicts revisits while also incorporating individual customer heterogeneity in exerted search effort during repeated visits. This heterogeneity is based on individual customer preferences in the choice of consideration sets, product information, pricing, and the search environment. Using customer level clickstream data, we show that our approach is not only better at predicting repeat customer visits, compared to existing methods, but also explainable and managerially interpretable. Most importantly, using computationally efficient simulation-based prescriptive analytics, we leverage our modeling approach to propose practical intervention strategies that maximize the joint likelihoods of customers revisiting and purchasing at the individual customer level.

How Does Competition Affect Exploration vs. Exploitation? A Tale of Two Recommendation Algorithms

Through repeated interactions, firms today refine their understanding of individual users’ preferences adaptively for personalization. In this paper, we use a continuous-time bandit model to analyze firms that recommend content to multihoming consumers, a representative setting for strategic learning of consumer preferences to maximize lifetime value. In both monopoly and duopoly settings, we compare a forward-looking recommendation algorithm that balances exploration and exploitation to a myopic algorithm that only maximizes the quality of the next recommendation. Our analysis shows that, compared with a monopoly, firms competing for users’ attention focus more on exploitation than exploration. When users are impatient, competition decreases the return from developing a forward-looking algorithm. In contrast, development of a forward-looking algorithm may hurt users under monopoly but always benefits users under competition. Competing firms’ decisions to invest in a forward-looking algorithm can create a prisoner’s dilemma. Our results have implications for artificial intelligence adoption and for policy makers on the effect of market power on innovation and consumer welfare. This paper was accepted by Dmitri Kuksov, marketing. Supplemental Material: The online appendix is available at https://doi.org/10.1287/mnsc.2023.4722 .

Studying optical properties of Gd<sub>2</sub>O<sub>3</sub>:Eu nanophosphor by Judd-Ofelt theory

Eu3+doped Gd2O3 nanophosphor were successfully obtained by a straightforward combustion method. The crystal structure and optical characteristics were investigated by methods: XRD, photoluminescence spectra (PL). The XRD result indicates the Gd2O3:5%Eu had cubic phase and the average particle size was about 32 nm. The photoluminescence showed the strong red emission with the 5D0-7F2 electric dipole transition was dominant. The intensities of 5D0-7FJ transitions depended on the symmetry of the local environment of Eu3+ ions and were described using the Judd–Ofelt analysis, using Ω2 and Ω4 intensity parameters derived from emission spectra data analysis. The calculated lifetime value was 1.8 ms and the quantum efficiency was 58,63%.

Influence of Thermal Maturity on the Time-Resolved Emission Spectrum (TRES) Fluorescence Lifetime Characteristics of Crude Oils: A Preliminary Study Based on a Thermal Simulation Experiment of Crude Oils

The time-resolved emission spectrum (TRES) fluorescence lifetime characteristics of crude oil have great application potential to classify the oil type and reveal its origin in a multisource petroleum system. However, the influence of thermal maturity on the TRES fluorescence lifetime characteristics of crude oil is still unclear. This study collected typical crude oil samples from deep reservoirs in the Tabei area of the Tarim Basin and obtained a group of pyrolyzed oils with different maturities by a thermal simulation experiment. The TRES average fluorescence lifetime value (τA) and profile pattern (λ–τ) of both pyrolyzed and crude oil samples were investigated. The results indicate that, with increasing maturity, the τA values of pyrolyzed oil slightly increase when EasyRo < 0.90% but decrease when EasyRo > 0.90%. Meanwhile, the λ–τ pattern shows no obvious changes when EasyRo < 1.53% but changes significantly when EasyRo > 1.53%. Based on the TRES fluorescence lifetime characteristics, the deep crude oils in various blocks of the Tabei area are divided into TB-I and TB-II types, which correspond well with their physical properties, diagnostic biomarkers, and carbon isotopic values. The TB-I crude oils are widely distributed in the Shunbei, Hadexun, Repu, and Halahatang blocks. This type of crude oil has a short τA value and exhibits an obvious platform pattern in its λ–τ profile. The TB-II crude oils are distributed only in the Yuke block. This type of crude oil has a long τA value and shows a unimodal pattern in its λ–τ profile. The TRES fluorescence lifetime parameters can effectively classify crude oils with different sources and can further identify the thermal maturity of crude oils with the same sources by combining them with the physical and geochemical parameters of crude oils, which exhibits great application potential to crude oils and individual petroleum inclusions in deep multisource petroleum systems.

Social Media Advertising for Achieving Long-term Marketing Objectives

Increasing competition in consumer markets forces businesses to elaborate marketing plans focused on long-term perspectives. This is important in today's fluctuating and unpredictable business environments, where a high level of competitiveness and a positive reputation is the premise of survival for a business. Otherwise, it will be unable to retain its share of consumer markets and make plans focused on long-term periods. In this regard, social media advertising is one of the most powerful strategies to reach various marketing goals: brand awareness and high brand value, positive reputation and word of mouth, growing customer base, high ROAS (return on ad spend) in short-term and CLV (customer lifetime value) in the long run. Therefore, it is necessary to research social media advertising to achieve long-term marketing goals. The paper deals with various issues, including social media advertising opportunities, ways of attracting and retaining customers, raising brand awareness, and elaborating strategies focused on long-term results. The discussion provided in the paper is a result of the literature review and the author's observations. Each part of the paper contains recommendatory remarks for achieving long-term marketing goals by using social media advertising strategies. A brief conclusion summarizes the paper.

The analysis of methodological approaches to the assessment of the efficiency of the enterprise’s marketing activity

The aim of the article. The purpose of the article is the analysis and generalization of the approaches to grouping and stages of the forming process of the system of the effectiveness and efficiency indicators of the enterprise’s marketing activity. Analyses results. The scientific community pays considerable attention to the study of financial aspects regarding the system formation of evaluating indicators of the enterprises’ marketing activity. Despite the sufficient interest paid to the problems of efficiency assessment by foreign and national marketing specialists there is no carefully structured system of the categories, methods and indicators that allow evaluating marketing activity. There are the approaches that recommend using only financial methods in evaluating the effectiveness of marketing activities, but in practice it has been proven that only the financial analysis is not enough to determine the effectiveness of marketing activities, since non-financial factors that also determine the financial effectiveness are neglected. Some scientists suggest using a general criterion of effectiveness to measure the effectiveness of marketing activities, namely, the ratio of the result of the company’s financial activity (provided that marketing services are functioning) to the costs of their maintenance. The group of non-financial indicators for evaluating the enterprises’ marketing activity is also very important. There are the following approaches: brand analysis, comparative analysis of the marketing complex, analysis of customer retention policy, customer lifetime value, model of predicting net income from the consumer relations, SCOR model. Such approaches can also include those that use a psychological component, which nowadays is very important regarding effectiveness evaluating of marketing activity. This article focuses, first of all, on the fact that it is necessary to clearly define the methodological principles on which the construction of the indicator system of marketing activity is based. Such an opinion is justified by the fact that when it becomes clear what principles the construction of the indicator system of marketing activity is based on and what requirements are put forward to this system, it is possible to proceed to detailing the process of evaluating the effectiveness of the enterprises’ marketing activity. Conclusions and perspectives for further research. The conducted research showed that the scientific community did not reach the agreement on the issue of developing precise methodological bases for the systematic assessment of the effectiveness of marketing activities. However, there is also a positive trend which is expressed in the fact that the use of various methods of evaluating marketing activity allows to compare the degree of effectiveness of conducting marketing activities at the enterprise, as well as the need and feasibility of implementing certain marketing measures. Each of these methods has advantages and disadvantages and the choice depends on the choice of goals and appraisal object. However, the scientific community unanimously holds the opinion that the assessment of the effectiveness of the enterprises’ marketing activities of any industry is necessary first of all in order to substantiate the importance of marketing for the enterprise activity, regardless of the industry, and to be able to improve the marketing strategy. In further developments in this area it is planned to rationalize and search for new methods and approaches for evaluating the effectiveness and contribution of marketing to the successful activity of enterprises.

Authenticity Business Model Canvas - A New Tool Applied to the Portuguese Way of St. James

The Authenticity Business Model Canvas is a tool to enhance the role of authenticity in business models. It was based on the combination of the Triple-Layered Business Model Canvas (TLBMC) proposed by Joyce and Paquin (2016) with the authenticity theory presented by Wang (1999). The model attempts to solve the challenge of helping companies identify sources for value creation by involving key stakeholders (particularly employees and customers) to improve the authenticity of the business. The research shows that the enhancement of object-based and existential authenticity, as well as relational value, contributes to increasing customer loyalty, customer lifetime value and word of mouth. This paper explains how the tool was developed through a case study applied to the Portuguese Way of St. James. The Authenticity Business Model Canvas is presented and its key features are described.

Quantifying the Impact: Evaluating Success Metrics and KPIs for Data Science Initiatives and ROI Optimization

In the dynamic intersection of business and technology, data science emerges as a linchpin for innovation and competitive advantage. This paper delves into the nuanced realm of success metrics and key performance indicators (KPIs) crucial for evaluating the impact and success of data science initiatives. Unveiling metrics such as accuracy, model performance, and business impact, it outlines the strategic importance of Return on Investment (ROI) and data quality in the data science landscape. This paper also provides a comprehensive guide for data scientists to implement and monitor these metrics, emphasizing the iterative nature of improvement. Illustrated through a case study on customer lifetime value (CLV), the piece underscores the role of success metrics in optimizing outcomes, showcasing the significance of continuous monitoring and improvement for organizations venturing into data-centric endeavors.

Management of Customer Lifetime Value in Organizations

Companies should focus on customer lifetime value, its management, and on profitable customers for company growth. The objective of the study is to analyze customer lifetime value and to manage it effectively. The methodology adopted is a conceptual analysis of various aspects of customer lifetime value and its management. Companies should appreciate the importance of customer lifetime value and the connections among customer lifetime value, brand equity, and customer equity. They should develop and build customer lifetime value through various measures (viz., improvement in customer services, customer engagement, enhancing the growth potential of customers, management of unprofitable customers, rewarding profitable customers, and developing customer touch points). They should develop customer loyalty through trust and measure customer lifetime value. Academicians may suggest models that are effective in measuring customer lifetime value and identifying profitable customers. Managers may suggest effective strategies and initiatives for better management of customer lifetime value.

Customer lifetime value: How understanding your current customers can help to find new ones

Customer lifetime value is a linear term that defines aggregate transactional value over time. Simply put, it represents how much a customer relationship is worth to an organisation. It is an important metric that businesses looking to scale need to understand and should evaluate how best to leverage. This paper seeks to expand the understanding and appreciation of customer lifetime value as a metric for making business decisions across the various marketing media.

MARKETING COMO OPÇÃO NA CONSTRUÇÃO DE RELACIONAMENTO COM CLIENTES

This study aimed to identify and describe the marketing strategies adopted by companies that aim to establish a lasting bond with their customers, with the aim of transforming them into allies in the search for continuous improvements in products and services. It also sought to highlight the return that these strategies can bring to the business, in addition to describing what companies do to understand their customers, aiming to develop close relationships with them, in order to constantly satisfy and even exceed their expectations. At first, the study describes the changes in the objective, focus and concept of marketing over the years, addressing how the relationship between companies and customers was and how it is seen, then the marketing strategies that companies have adopted with a view to creating and establishing a lasting relationship with their customers are discussed and, finally, the return that can be obtained by companies that seek to establish a consistent and lasting relationship with their customers is addressed. The conclusions indicate that, currently, customer loyalty and the lifetime value they represent are essential factors for companies, and that customers are preferring companies that, in addition to satisfying their needs, seek to establish a long-term relationship.

Research on customer lifetime value based on machine learning algorithms and customer relationship management analysis model

Customer lifetime value is one of the most important tasks for enterprises to maintain customer relationships. However, due to the limitations of using a single data mining method, the measurement of customer lifetime value under the condition of noncontractual relationship has always been a research difficulty. This paper focuses on customer value measurement and customer segmentation based on customer lifecycle value theory, and carries out customer value measurement and customer segmentation research from the perspective of customer value, and constructs customer segmentation model. This paper first conducts feature engineering, such as data selection, data preprocessing, data transformation, and knowledge discovery, and then conducts customer value segmentation based on machine learning algorithms and customer relationship management analysis models and builds a customer value segmentation identification model under the condition of noncontractual relationship. Finally, empirical analysis is carried out with the real customer transaction data of the actual online shopping platform, which verifies the validity and applicability of the customer segmentation method and value calculation method proposed in this paper.

Customer lifetime value: the effect of relational benefits, brand experiences, quality, satisfaction, trust and commitment in the fast-food restaurants

PurposeThis study examines factors that affect customer lifetime value (CLV) in fast-food restaurants (FFRs) in Jordan. These factors are relational benefits, brand experiences, service quality (SQ), satisfaction, trust and commitment.Design/methodology/approachAn online survey was collected from a sample of 503 respondents. The authors used SPSS to test the constructs' relationships and analyse the data. SmartPLS was used to test the hypotheses.FindingsIn contrast to previous studies, not all dimensions of brand experiences and relational benefits had a significant and positive influence on relationship marketing outcomes (satisfaction, trust and commitment). On the other hand, results demonstrated that SQ had a significant and positive influence on relationship marketing outcomes. Furthermore, research reveals that satisfaction, trust and commitment significantly and positively influenced CLV.Practical implicationsThose FFRs that seek to enhance CLV should build solid and sustainable bonds with their customers. This paper concludes by stating its implications, its limitations and the opportunities available for future research.Originality/valueThis study, which is unique in the Middle East, includes essential strategies for managing customer relationship that can be universally applied to improve customer benefits and maximise the performance of businesses.

Economic value of knowing BRCA status: BRCA testing for prostate cancer prevention and optimal treatment

ABSTRACT Background We aimed to estimate the incremental lifetime effects, costs, and net-monetary-benefit (NMB) of knowing BRCA information by testing of patients with low-risk localized prostate cancer (PCa) in the US and guiding subsequent screening and treatment, and the cumulative savings or losses of yearly cohort testing over 16 years. We compared two strategies: (1)‘with BRCA information’ and (2)‘without BRCA information.’ We also estimated the expected value of perfect information. Methods The incremental NMB (INMB) quantified the monetized benefit per person of knowing BRCA status. The net-monetized-value of knowing BRCA information was estimated by multiplying the INMB with the eligible population. Results The INMBs of knowing BRCA information were $43,357 (payer) and $43,487 (society). in payer and societal perspectives, respectively. Escalated to the eligible patients in 2020, knowing BRCA status resulted in net monetized lifetime value of $1.7 billion (payer and society) for the 2020 cohort; and yielded accumulated net-monetized-value of $28.0 billion (payer) and $28.1 billion (society) over 16 yearly cohorts of eligible PCa patients. Conclusions The economic value of knowing BRCA status for all low-risk localized PCa patients in the US provides short-term and long-term evidence for BRCA testing to screen early and optimize treatment.

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.

Dye-sensitized solar cells with efficiency enhancement surpassing 65% through layer-by-layer assembled plasmonic photoanodes

Even though plasmonic photoelectrodes have paved the way for high-efficiency DSSC, metal nanoparticle degradation in iodine-based electrolytes restricts commercialization. In order to protect the plasmonic nanoparticles, the plasmonic photoelectrode having a layer-by-layer assembly of TiO2/Ag/TiO2 has been developed by a simple photoreduction at various time intervals followed by mild TiCl4 treatment over the TiO2 film and fabricated into dye-sensitized solar cells (DSSC). On evaluating the performance of fabricated DSSC under AM 1.5 G irradiation with the intensity of 100 mWcm−2, the champion cell (η = 11%) shows 65% enhancement in power conversion efficiency compared to the pristine TiO2 photoanode-based DSSC (η = 6.67%). The photocurrent density has been improved due to the surface plasmon resonance effect of Ag nanoparticles and the formation of TiO2 by TiCl4 treatment not only protects the Ag metal nanoparticles as well as creates more dye-loading sites. A negative shift in the Fermi-level caused by the accumulation of electrons in Ag, triggers the open-circuit voltage to increase by 100 mV which is evident from the Mott-Schottky analysis. The electron lifetime value is increased due to increased charge collection efficiency. The champion cell shows 91.5% retainment in efficiency even after 5 days.

IMPLEMENTASI K-MEDOIDS DAN MODEL WEIGHTED-LENGTH RECENCY FREQUENCY MONETARY (W-LRFM) UNTUK SEGMENTASI PELANGGAN DILENGKAPI GUI R

The k-medoids algorithm is a partition-based clustering algorithm that groups n objects as much as k clusters. The algorithm uses medoids as the center point (partition) of the cluster. Medoids are actual objects that are randomly selected as the most centered object in a cluster so that the k-medoids algorithm is robust against outliers. Grouping objects in cluster analysis based on similarities between objects. Measurement of similarity between objects can use the euclidean and manhattan distances. The use of distance in cluster analysis can affect cluster results. Validation of cluster results using internal validation, namely the silhouette index. The Weighted-Length Recency Frequency Monetary (W-LRFM) model is a model that applies the relative importance (weight) of the LRFM model according to the importance of each variable in the LRFM model. LRFM model is a model used for customer segmentation based on customer behavior which consists of variables length, recency, frequency, and monetary. The relative importance (weight) of the W-LFRM model uses the Analytics Hierarchical Process (AHP) method. The W-LRFM model is used to calculate the Customer Lifetime Value (CLV) of each cluster. The implementation of k-medoids and the W-LFRM model in this study are used for customer segmentation based on the length, recency frequency, and monetary variable. The formation of these variables is the result of transformation of customer behavior data such as transaction id, date of purchase, and a total amount of 41,073 rows into variable length, recency, frequency, and monetary as much as 5,108 rows. The criteria of the best cluster formed are k = 2 using the manhattan distance with the average of coefficient values = 0.62. The weights on the W-LRFM model produced based on the AHP method are 0.16, 0.29, 0.47, and 0.08 for the variable length, recency, frequency, and monetary. CLV formed from two clusters, namely 0.158 and 0.499. CLV in the second cluster is bigger so that the second cluster becomes the main priority in the marketing strategy. The second cluster has the characteristics 0.29, 0.47, and 0.08 for the variable length, recency, frequency, and monetary. The second cluster has the characteristics means a loyal customer group. The first cluster has characteristics means a potential customer group. This research is assisted by using Graphical User Interface (GUI) R to facilitate analysis

The impact of customer clubs on lifetime value of banking customers

Today, with the abundance of private banks, state-owned banks and financial and credit institutions, banks are trying to satisfy customers more than ever in order to be preferred by them. In this regard, they use customer clubs as a communication network to improve their up-selling, cross-selling and word of mouth marketing. Therefore, this study aims to investigate the short-term impact of customer clubs on the lifetime value of customers as one of the most important indicators that reflects customer satisfaction, loyalty and thereby financial gain. To this end, the RFM model was used for clustering customers based on their behaviours. Then customers' lifetime value for each cluster was calculated in four periods. The state transition probability matrix of a Markov chain was also used to analyse the customers' transitions and change in their values through the seasons. The results indicated that customers' lifetime value and the number of profitable customers increased in the last period in which the customer club was used.

Using Field Experiments to Infer Cross-Side Network Effects in the Ride-Sharing Market: How Does Driver Supply Impact Rider Orders, Cancellations, and Customer Lifetime Value?

Using Field Experiments to Infer Cross-Side Network Effects in the Ride-Sharing Market: How Does Driver Supply Impact Rider Orders, Cancellations, and Customer Lifetime Value?