Abstract
Customer relationship management is essential because companies are customer-centric, especially in new business models. In some sectors, each individual customer can determine the company’s success in a significant extent. A well-founded decision-making process reduces the number of critical situations, particularly in volatile markets. Furthermore, a trustful customer relationship has several advantages, for example, reduced transaction costs with less information asymmetries. A forward-looking customer relationship management anticipate relevant factors at an earlier stage in the decision-making process. New business models require a more precise customer and accompanying risk analysis, which allows an effective view of the customer’s life cycles. In this context, an innovative management accounting approach for customer relationships is necessary. The managerial implications derived from such processes crucially hinge among other things on the risk assessment. Consequently, this article presents a systematic customer-oriented calculation approach to evaluate customer relationships in new business models. Considering the multifactorial perspective, simulation techniques are a useful approach to solve sophisticated decision situations for shaping customer relationships. The introduced approach can be transferred to other sectors with important customer-centric relationships.
Keywords
- new business models
- innovative business models
- customer relationship management
- customer life-cycle management
- customer value
- volatile markets
- decision-making
- managerial accounting
- management accounting
- customer-oriented risk management
1. Introduction
There are many studies about
The extent of methodological support depends on enterprise size. A standardized customer relationship analysis is essential for all companies. Single (risk) factors are often examined in a qualitative rather than in a quantitative way. For instance, knockout criteria are used on the basis of historical costs, and methodologically poor substantiated risk premiums are applied. However, the situation is exacerbated if similar risk premiums are used for export markets with different risk levels.
In this context, an entire set of ambitious
What are relevant factors for assessing customer relationships in new business models?
Which factors must be included in the customer evaluation process?
How can a decision-oriented approach for evaluating customer relationships (that is based on management accounting principles) be structured?
What recommendations can be derived from a well-founded calculation approach conducted for customer relationship management?
This article addresses these important questions through the following steps. First, the methods are specified to accurately represent the characteristics of new business models for internal management decisions. Such considerations require, more than other calculation problems, a well-founded risk consideration. The methodological approach is based on decision-making theory.
To solve complex tasks using the principles of management accounting, a few additional steps are necessary, for example, the integration of a year-specific approach with overlapping cash flows and with a simulative calculation of a customer relationship profile. An important contribution to knowledge consists in the transfer of the decision-oriented accounting view to customer-centric questions.
Considering a risk-oriented management perspective,
The remainder of the paper is organized as follows. Section 2 discusses the theoretical background of customer relationship management from a managerial accounting perspective in the context of new business models. Section 3 systematized and describes the key factors for a risk-oriented evaluation process in new business models to recommend a methodological approach for customer relationship management. Section 4 specified the suggested risk-oriented approach. Section 5 shows essential steps of the evaluation process. Finally, Section 6 concludes the article.
2. Theoretical background for evaluating customer relationships in new business models
2.1 Principles for evaluating customer relationships in new business models
Before the details of the evaluation process for customer relationships can be described, a
The second principle, PoR, is an important aspect of simplification. The relevant question is which position (respectively which items) are relevant for the decision in the case-specific valuation process. Only differences between alternatives are relevant in the evaluation process. All other factors can be omitted from comparative calculation methods.
PoM highlighted the marginal modifications in a decision situation. Only marginal costs and revenues are considered, and no average values are included. The last principle, PoE, requires an assessment process for each individual calculation item in all individual situations. For instance, a bottleneck scenario requires a totally different assessment than a non-bottleneck situation. This paper will apply those principles for management decisions to a customer lifetime approach under risky decision conditions in new business models.
2.2 Life cycle analysis as structural basic concept for evaluating customer relationship management in new business models
The
Due to cost considerations, it would be useful to differentiate between at least three levels in the life cycle analysis [10]. The
Life cycle considerations are particularly important for new business models as the payments extend over several periods. Life cycle analyses are integrative and flexible. Therefore, this approach is well suited for new business models and volatile markets.
2.3 Risk-based evaluation process of customer relationships in new business models
New business models are risky in different dimensions. Therefore, a company should integrate risk management into customer management in a detailed way. A risk-oriented calculation approach for the customer relationship should include all relevant
Modeling dependencies between products over the customer’s lifetime is one relevant aspect. For instance, a follow-up project is planned following the successful completion of a project. The likelihood of obtaining the follow-up project is connected to the previous experience of the customer relationship so that this case cannot be considered independently of the previous interaction process. Trust is an important factor influencing the future probability of a project. The initial project’s successful implementation increases the assignment probability for the follow-up project.
The expected costs of customer relationship management depend on customer characteristics. Therefore,
The effort, frequency, and timing of relationship management must be forecast separately for each customer relationship class. In such cases, a further differentiation is necessary in the life cycle analysis. Figure 1 shows schematically the structure between the recording of customer-oriented basic concepts and the subsequent further processing of the lifetime calculation. The detailed procedure corresponds to the presented risk-oriented approach in the previous chapter.
3. Selected key factors for the risk-oriented evaluation process of customer relationships in new business models
3.1 Integration of cross- and up-selling potentials in the customer evaluation process for new business models
New business models are typically not only based on the sale of a product at a specific point in time. The aim of new business models is normally to retain a
All target effects must be taken into account for the evaluation of the customer. For this reason, the category, in which the potentials are classified, is less important for the evaluation process. The focus lies on the
When we evaluate cross-selling potential, it is important to consider the year-specific effects. Different potentials can be assumed in each customer relationship, which must be exploited through targeted customer management.
The most obvious effect resulting from the exploitation of cross-selling potential is the extended coverage of demand through
3.2 Integration of customer-based references in the customer evaluation process for new business models
Especially in mechanical and plant engineering, recommendations and testimonials are an important instrument for supporting sales. By passing on positive and negative experiences about perceived features of the manufacturer and its products (but also through the exchange between manufacturers about customer behavior) existing uncertainties can be reduced. These cases will be summarized as
These potentials can be taken into account in different ways. One possibility is the direct estimation of a
4. Risk-oriented approach as a connecting element for evaluating customer relationships in new business models
4.1 Customer-oriented risk decomposition for a well-founded evaluation process
Developing new business models can be risky and customer-specific risks can be reflected in different parts of the value chain. If, for example, a manufacturer has to decide to accept the request of a foreign customer to deliver a machine that is domestically successful, then risks concerning domestic markets are irrelevant. For instance, special documentation requirements for an operating license can be regarded as a risk variable that can cause penalties of missed on-time deliveries. An effect similar to that of such export specifics can be caused by order specialties. Another example is the case of a customer project having a positive effect on other potential customers. In such cases, the probability changes must be taken into account. A risk-oriented checklist is an important approach to reduce wrong decisions in customer relationship management. The basic concept behind this instrument is to split the evaluation of the current situation and the forecast for future parameters into
Risk checklists differ among operational areas of the value chain. As a result, a
A relevant issue in designing risk checklists is the
For evaluating customer relationships, we use the structure of the net present value (e.g., [16, 17, 18]). Applying a hierarchical structure of the checklist system within the risk analysis is helpful. In this way, the analytic process can be arranged regardless of whether certain risk elements should be analyzed in a detailed way. Hence, an extensive analytical effort can be concentrated on the most important partial risks. This can be managed by applying the individual risk-oriented thresholds of the user. The thresholds emerge from a consideration between the achievable information gain achieved by a finer risk analysis and the acquisition effort necessary to manage customer relationships.
From the starting level of the checklist hierarchy, predetermined values of customer-oriented risks can be found. When further risk thresholds are exceeded, they are broken down into single positions. This can affect revenues and cost positions, as well as year-specific dwell time factors.
A product based and more detailed risk-oriented calculation approach can be supported by a
4.2 Identification of customer-specific risk components to design an evaluation model for customer relationships in new business models
Variables with risk-influencing factors can be referred to as risk factors or risk drivers. The collaboration of various risk drivers is one reason for the special issues involved in evaluating customer relationships. Risk drivers can be differentiated according to where they originate, whether they are the result of a company’s own decision or whether they are primarily attributable to external drivers. Figure 4 shows typical examples—especially in the case of new product bundles—of risk-influencing factors in the calculation of customer relationships.
A finer distinction can be made for
5. Methodological approach for evaluating customer relationships with management accounting
5.1 Evaluation levels for customer relationships in new business models
The evaluation of a customer relationship in new business models can, for example, involve the direct sale of products. Customers are visible. Therefore, each customer can be distinguished from the company. In other segments, customers are not visible to the manufacturer in a detailed way. In such situations, standard hypotheses are required for a customer segment. Figure 5 shows the different assessment levels for risk-oriented life cycle analysis in customer relationship management.
For a more accurate risk assessment, it is advisable to start with the evaluation of customer relationships at the most granular level. In some segments, for example, in new business models or in order-related production, just a few customer relationships can already make a significant contribution to the success of the enterprise [19]. The loss of a handful of major customers can easily jeopardize the existence of the business. Moreover, not every customer is lucrative over the customer lifetime. An evaluation that focuses on the individual customer is more successful if the customer is visible and approachable for the manufacturer. For example, it may be advantageous to prioritize a rather risky basic project with a new customer in a different sales market situation over a standard regional customer order because this project can have a significant impact on the future customer relationship. Furthermore, effects on other customers can be assumed, for example, through a positive verbal recommendation or a higher cross-selling potential [20, 21, 22, 23]. It is an essential factor why an isolated average period-related customer evaluation falls too short. In such cases, it is necessary to classify customer relationships on the basis of customer potential over time. Under these circumstances, the evaluation of customer relationships is made more difficult by the fact that an isolated product evaluation cannot be assumed, particularly in the case of repeated interaction between manufacturer and customer. This aspect leads to an intensified risk situation.
A cross-product consideration of the customer relationship becomes an important aspect in the risk-oriented calculation approach for customer relationship management [10]. Such a consideration is all the more expedient when partial services are offered at sales prices that are obviously only justified because the manufacturer expects the customer to order additional services at a later date. This is an important reason for the manufacturer to lead the customer into a system of a sophisticated and usually modularized package. In such a case, the product is offered as a bundle of coordinated services. As a result, the scope for decision-making at a later stage is limited. Consisting of several individual components, it is set up not only to cover the customer’s current needs but also to determine and fulfill the requirements as completely as possible throughout the entire customer relationship. In addition, a dependency relationship between the manufacturer and the customer can develop, and the service bundle extends over time. All of these individual elements are typical of customer relationship assessment with life cycle analysis.
The evaluation process of a customer relationship is confronted with factual and temporal allocation difficulties. In the literature, a customer lifetime value is regularly proposed as a key performance indicator to solve such problems [16, 17, 18, 24, 25, 26, 27, 28, 29, 30]. This measure can be interpreted broadly, but the approach is often combined with limiting hypotheses (e.g., [31]). The underlying standard expectations may fail in the risk analysis. For example, the costing approach regularly assumes that the associated consequences will be completed within the sales period. In addition, average costs for each customer relationship are assumed [10, 31, 32], and sometimes, the cash flows are corrected by different factors that attempt to take the average risk into account. The standard assumptions lead to mismanagement. For example, the costing approach regularly assumes that the associated consequences will be completed within the sales period. In addition, average costs per customer relationship are assumed [31, 32], and occasionally, the cash flows are adjusted by various factors that are intended to take the average risk into consideration. These techniques only make sense if no cross-period effects are to be expected, regular sales of constant products are assumed, and no more precise forecasts appear realistic. In the standard case, such a limited situation does not occur. In many cases, a detailed information base about customers is available. At the very least, the specialists can define certain parameters as a range for the relevant values, for example, engineers, sales staff, and managers. Incorporating standard assumptions on a frequent basis does not appear to make sense in this context. Product-related information is also useful for customer analysis. These analyses should be supplemented by customer-related risk factors. In this analysis, several payments will overlap over time [10, 13].
5.2 Evaluation process for customer relationship management in new business models
Risk management is determined by different probability functions and a complete recording of the identified partial risks. Two relevant sub-aspects within this management task are the type of partial risk measurement and the subsequent risk aggregation. In general, these issues occur even without the use of standardized risk checklists with threshold control. However, the approach used determines the procedure and the question technique in general. For example, the best approach depends on whether absolute heights or only change rates are available from the expert. Sometimes, simply additive target values are used to minimize the planning effort. This causes inaccuracy in the calculation. If we restrict ourselves to simply summable target values, then the complexity of the acquisition is partly downgraded to an operator level.
Another important question concerns the aggregation of risk profiles into a probability distribution of target parameters. Especially, in the case of different types of probability distributions or in the case of risk interdependencies between risk factors, the aggregation of different risk profiles is nontrivial. In many instances, an exact concept is impossible or very restrictive. Therefore, simulations are frequently used. For a simulative approach, a few steps are necessary to determine the sufficient net present value for the customer relationship. Figure 6 schematically shows the structure between the recording of customer-oriented risks with checklists and the subsequent further processing of the lifetime calculation.
A customer-oriented calculation approach can also account for risk interdependencies. This concept is based on a year-specific measurement method. Therefore, the influencing variables can change within each period and over time. Such an approach permits the integration of time lag effects, for example, changes in purchasing behavior following a special advertising campaign. It can also be used for the calculation of price limits, for example, for special marketing actions or a cross-subsidization.
After risk aggregation to the net present value of the customer contribution margin, the risk profiles can be analyzed separately or condensed into a single key performance indicator. The last step is an assessment process of information aggregation and the exhaustion of management capacities. Therefore, it is not only a formal step in the decision process. In the case study, we consider both alternatives to derive recommendations for management decisions.
5.3 Integration of all relevant factors with simulations for evaluating customer relationships in new business models
Simulations are standard tools in a wide range of research fields. They can be used to satisfactorily solve complex problems [29, 33, 34], and the method is not limited to special applications [13]. The core idea of simulation approaches in this context is based on the model of Hertz [35]. The probability distribution of a target variable is obtained by a repeated target value calculation made from an available dataset of input variables, where the input parameters are selected in consideration of their probability distributions. In contrast to the use of an exact approach, not every case can be analyzed. The consequence is a decision problem (represented by the simulation model) that provides no exact solution but only an approximately accurate output. In the end, this is not quite relevant for decision-making, as long as the decision maker accepts the results. Simulations are an experimental approach [35] in which one or more independent variables are manipulated, and their effects, along with the control of all other variables, on the dependent variable are examined. The simulative procedure is based on several identical calculation steps. In each simulation run, a characteristic of each variable is chosen according to the probability distribution to calculate the corresponding outcome from a set of input data.
Simulations are suitable for those model analyses that exceed the solution power enabled by a closed-formula method. This approach is common, especially when the methodology is opened for different types of functions, for example, in a recommended year-specific manner. Such approaches have a reputation of being associated with daunting efforts in preparation and implementation. In general, there are two aspects that should be distinguished. It is undisputable that initial preparation is connected with some additional considerations. However, similar efforts would be expected in other calculation approaches for management decisions, provided that the issue is approached in a decision-oriented and analytical manner. Therefore, this aspect can also be seen as a typical characteristic of the systematic information gathering and evaluation of a decision situation in management accounting. As soon as the analytical calculation structure has been established, the number of simulation runs can be increased rapidly without any major effort. The algorithm usually requires manageable computing power and memory capacity.
While simulations are not necessary for the consolidation of the previous results, they certainly appear to be specifically recommendable because of the extensive scope of the relevant application. Figure 7 summarizes the simulation steps, whereby the probability functions are considered by the evaluation process. On the one hand, this approach is not restricted to any particular distribution type. On the other hand, dependency relationships between influencing variables can also be taken into account, for example, conditional probability statements. It is also possible to include bivariate functions or other higher-order functions. In this situation, the calculation structure does not limit the variety of representations.
Figure 8 shows an example of the risk profile of two potential customers as a result of the evaluation process. This detailed approach can be used to derive specific recommendations for action, such as the risk associated with a customer relationship, whether the target figures are being achieved, or whether measures need to be initiated.
The expected risk can be assessed in a direct comparison between customers: Customer relationship B is riskier than customer A. The management must use this information to decide which risk should be accepted and which risk is too high.
6. Conclusion
The aim of this chapter is to assess a new methodological approach following the
Typical assumptions behind the
The methodology presented in this article offers several starting points for the detailed modeling of different effects [13]. For example, certain parameters can be directly included in the calculation with the expected parameter value. These would contain all contractually fixed agreements. For uncertain parameters, the predicted probability distributions are considered to be customer-oriented hypotheses. For such purposes, it is useful to take the information of several business experts into account. For example, the reduction in transaction costs (which can be expected over time) can be specified for each customer class. When we identify mismanagement in an early stage of the decision-making process, we can implement a forward-looking system to increase resilience agility, and reduce transaction costs.
It is primarily the task of management accounting to coordinate information between different organizational units, for example, through the use of a standard data collection structure with
The provision of a profound and risk-oriented analysis, a high level of risk transparency, and proactive risk management are key factors in the decision-making process for new business models. A risk-oriented extension of the customer assessment improves the management decision-making process in several ways. Especially, for small or medium-sized enterprises, a detailed calculation approach is essential, given that a relatively few customers can have a major impact on the success of the entire enterprise. Therefore, enterprises should focus on particularly important customer relationships to exploit their existing potential in new business models. Prioritization becomes possible, and risk potential can be assessed.
Particularly a disproportionately high risk in a customer relationship can also be filtered out. In this vein, such a focus enables periodic, just-in-time, and proactive adjustments, which can also be used for management approaches and
The approach is customizable in a flexible way. For example the concept is not restricted to any distribution functions. The risk-oriented life cycle assessment can be applied to identify the benefits of customer relationships. Various factors and additional information can be taken into account in different modes, for example, expected dependencies between various risk factors
It is conceivable that the available data only allow for very rudimentary customer-related forecasts. In this case, it is still possible to use a likely expected
For goal-oriented coordination in the management area, it is important to validate the information provided in the ongoing process and adequately include this information in the calculation approach. The focus should be on the data basis and the appropriate integration in the calculation approach.
In the evaluation process of customer relationships, different questions can be explored. During customer relationship management, for example, the question of the justified maintenance of the customer and the scope of customer care is particularly relevant to the evaluation process. For such questions, logical decision-making and well-founded calculations must be conducted throughout the accompanying preparation of information to obtain suitable management recommendations on a case-by-case basis for new business models. Such considerations are also combined with sensitivity analyses so that the corresponding stability limits are well-known for example, the price limits. These results can also be used in negotiations with the customers. In any case, this approach is better than other generalized recommendations. An analogous argumentation can be found in value-based management, especially in the shareholder value concept. Certain phases can be better predicted, and these should be more precisely represented in the calculation. If at least some parameters indicate that a longer-term business relationship is to be expected, then the second phase should not be abridged.
In principle, information allocation as a standard instrument in management accounting is sometimes, mainly associated with a standardized documentation task. However, in most cases, there is an important coordinative purpose associated with reporting. For this reason, well-founded data must be adequately
References
- 1.
Casas-Arce P, Martínez-Jerez FA, Narayanan VG. The impact of forward-looking metrics on employee decision-making: The case of customer lifetime value. Accounting Review. 2017; 92 (3):31-56. DOI: 10.2308/ACCR-51554 - 2.
Henschel T. Risk Management Practices of SMEs. Evaluating and Implementing Effective Risk Management Systems. Berlin: Erich Schmidt; 2008 - 3.
Kumar V, Pansari A. National culture, economy, and customer lifetime value: Assessing the relative impact of the drivers of customer lifetime value for a global retailer. Journal of International Marketing. 2016; 24 (1):1-21. DOI: 10.1509/jim.15.0112 - 4.
Petersen JA, Kumar V. Perceived risk, product returns, and optimal resource allocation: Evidence from a field experiment. Journal of Marketing Research. 2015; 52 (2):268-285. DOI: 10.1509/jmr.14.0174 - 5.
Raman K, Shahrur H. Relationship-specific investments and earnings management: Evidence on corporate suppliers and customers. Accounting Review. 2008; 83 (4):1041-1081. DOI: 10.2308/accr.2008.83.4.1041 - 6.
Sunder S, Kumar V, Zhao Y. Measuring the lifetime value of a customer in the consumer packaged goods industry. Journal of Marketing Research. 2016; 53 (6):901-921. DOI: 10.1509/JMR.14.0641 - 7.
Aba Bulgu M, Islam SMN. Corporate Crisis and Risk Management: Modelling, Strategies and SME Application. Leeds, Emerald: Publishing Limited; 2007 - 8.
Alquier AMB, Tignol MHL. Risk management in small- and medium-sized enterprises. Production Planning and Control. 2006; 17 (3):273-282. DOI: 10.1080/09537280500285334 - 9.
Ewert R, Wagenhofer A. Management accounting theory and practice in German-speaking countries. In: Chapman CS, Hopwood AG, Shields MD, editors. Handbooks of Management Accounting Research. Vol. 2. Amsterdam: Elsevier; 2006. pp. 1035-1069. DOI: 10.1016/S1751-3243(06)02021-9 - 10.
Röser M. More certainty in uncertainty: A special life-cycle approach for management decisions in volatile markets. Journal of Management Control. 2024; 34 (3):1-33. DOI: 10.1007/s00187-023-00364-z - 11.
Höft U. Lebenszykluskonzepte: Grundlagen für das strategische Marketing- und Technologiemanagement [Life-Cycle Concepts: Fundamentals for Strategic Marketing and Technology Management]. Wiesbaden: Erich Schmidt; 1992 - 12.
Kemminer J. Lebenszyklusorientiertes Kosten- und Erlösmanagement [Life-Cycle Oriented Cost and Revenue Management]. Wiesbaden: Springer; 1999 - 13.
Röser M. Produktbasierte Bewertung von Kundenbeziehungen im Maschinen- und Anlagenbau [Product-Based Evaluation of Customer Relationships in Mechanical and Plant Engineering]. Wiesbaden: Springer Gabler; 2022 - 14.
Cornelsen J. Kundenwertanalysen im Beziehungsmarketing [Customer Value Analysis in Relationship Marketing]. Wiesbaden: Springer; 2000 - 15.
Rudolf-Sipötz E. Kundenwert: Konzeption, Determinanten, Management [Customer Value: Concept, Determinants, Management]. Wiesbaden: St. Gallen; 2001 - 16.
Berger PD, Nasr NI. Customer lifetime value: Marketing models and applications. Journal of Interactive Marketing. 1998; 12 (1):17-30. DOI: 10.1002/(SICI)1520-6653(199824)12:1<17::AID-DIR3>3.0.CO;2-K - 17.
Gupta S, Hanssens D, Hardie B, Kahn W, Kumar V, Lin N, et al. Modeling customer lifetime value. Journal of Service Research. 2006; 9 (2):139-155. DOI: 10.1177/1094670506293810 - 18.
Kumar V. A theory of customer valuation: Concepts, metrics, strategy, and implementation. Journal of Marketing. 2018; 82 (1):1-19. DOI: 10.1509/JM.17.0208 - 19.
Röser M. Verallgemeinerte Deckungsbeiträge für Verbundprodukte nach Methoden der Lebenszyklusrechnung [Generalized contribution margins for composite products based on life cycle methods]. In: Arbeitskreis Internes Rechnungswesen der Schmalenbach-Gesellschaft, editor, Verbundprodukte. München: Vahlen; 2022. pp. 186-211 - 20.
Erat S, Bhaskaran SR. Consumer mental accounts and implications to selling base products and add-ons. Marketing Science. 2012; 31 (5):801-818. DOI: 10.1287/MKSC.1120.0731 - 21.
Ghoshal A, Mookerjee VS, Sarkar S. Recommendations and cross-selling: Pricing strategies when personalizing firms cross-sell. Journal of Management Information Systems. 2021; 38 (2):430-456. DOI: 10.1080/07421222.2021.1912930 - 22.
Kwiatkowska J. Cross-selling and up-selling in a bank. Copernican Journal of Finance & Accounting. 2019; 7 (4):59-70. DOI: 10.12775/CJFA.2018.020 - 23.
Schmitz C, Lee YC, Lilien GL. Cross-selling performance in complex selling contexts: An examination of supervisory- and compensation-based controls. Journal of Marketing. 2014; 78 (3):1-19. DOI: 10.1509/JM.12.0421 - 24.
Baidya MK, Maity B, Ghose K. Innovation in marketing strategy: A customer lifetime value approach. Journal of Business and Management. 2019; 25 (2):71-97. DOI: 10.6347/JBM.201909_25(2).0004 - 25.
Bursk EC. View your customers as investments. Harvard Business Review. 1966; 44 (3):91-94 - 26.
Hoekstra JC, Huizingh EKRE. The lifetime value concept in customer-based marketing. Journal of Market-Focused Management. 1999; 3 (3/4):257-274. DOI: 10.1023/A:1009842805871 - 27.
Jackson BB. Winning and Keeping Industrial Customers. Lanham: Lexington; 1985 - 28.
Kotler P. Marketing during periods of shortage. Journal of Marketing. 1974; 38 :20-29. DOI: 10.2307/1249846 - 29.
Rust RT, Kumar V, Venkatesan R. Will the frog change into a prince? Predicting future customer profitability. International Journal of Research in Marketing. 2011; 28 (4):281-294 - 30.
Zhang H, Liang X, Wang S. Customer value anticipation, product innovativeness, and customer lifetime value: The moderating role of advertising strategy. Journal of Business Research. 2016; 69 (9):3725-3730. DOI: 10.1016/j.jbusres.2015.09.018 - 31.
Heldt R, Silveira CS, Luce FB. Predicting customer value per product: From RFM to RFM/P. Journal of Business Research. 2021; 127 :444-453. DOI: 10.1016/j.jbusres.2019.05.001 - 32.
Méndez-Suárez M, Crespo-Tejero N. Why do banks retain unprofitable customers? A customer lifetime value real options approach. Journal of Business Research. 2021; 122 :621-626. DOI: 10.1016/j.jbusres.2020.10.008 - 33.
Evans JR, Olson DL. Introduction to Simulation and Risk Analysis. 2nd ed. New Jearsey: Thexis; 2002 - 34.
Rubinstein RY, Melamed B. Modern Simulation and Modeling. New York: Wiley; 1998 - 35.
Hertz DB. Risk analysis in capital investment. Harvard Business Review. 1964; 42 :95-106