28. CUSTOMER LIFETIME VALUE 2

OBJECTIVE

Estimate the retention and future spending amount of customers.

DESCRIPTION

In the previous chapter I explained the principles of CLV and its calculation. However, one of the problems was the estimation of the retention rate (for which the simplification was to apply the average retention rate of similar customers) and future spending amounts (we assumed that the average spending amount of each customer will not change in the future). Despite the facility of the implementation of this approach, it can be much too simplistic and fail to estimate CLV reliably.

There are several methods for estimating retention and spending amounts, but some of them can be far too complex. The method that I will propose has a good balance between accuracy and implementation simplicity and is based on customer segmentation and probability.

The first step is to take the customer data of year -2 and segment them based on their value and their activeness. For the value we can use the amount spent in a specific year (which is a mix of the average amount spent per purchase and the frequency of purchases), and for activeness we can use the recency of the last purchase (for example the number of days between the last purchase and the end of the analyzed year). For activeness we can also use a mix of recency and frequency. In the second step, we have to define a certain number of customer segments. The segmentation technique can be either a simple double-entry matrix or a statistical clustering technique. We can for example end up with six clusters:

• -          Active high value
• -          Active low value
• -          Warm
• -          Cold
• -          Inactive
• -          New customers

The idea behind this technique is to estimate the retention and spending amount using the probability of a customer remaining in the same segment or changing segment and by applying to this customer the average spending amount of the new segment. To calculate the probability of moving from one segment to another, it is necessary to segment the customers into year -1 and create a transition matrix (transition among different segments from year -2 to year -1) in which probabilities are calculated for each combination of segment groups.

Transition Matrix of Customers’ Segments

With the probability transition matrix we can simulate how the segments will change in the future and maybe realize that we are dangerously reducing active customers in favor of inactive ones and that we need to acquire a slightly bigger number of each kind of customer to avoid a decrease in profits. In any case with this matrix we can simulate several years ahead and estimate how many customers will still be active. We can also estimate their value by multiplying the average value of each segment by the number of customers of the same segment in a specific year (year 0, year +1, year +2, etc.).

In the proposed template, I have added an estimation of new customers acquired each year to simulate the total number of customers and their value a few years ahead. However, to calculate the CLV of the current customers, this value should be set to 0 and then the total value of each year discounted by the discount rate.

TEMPLATE

Download the CLV2 Template

76. GAME THEORY MODELS

OBJECTIVE

Anticipate competitors’ strategic decisions.

DESCRIPTION

Demand forecast or pricing models aim to find the optimal solution to maximize the benefits. However, this optimization usually does not take into consideration the fact that competitors are not static actors and will probably react to strategic decisions.

Game theory models take into account other players’ actions, and they offer theoretically an equilibrium in which no player can be better off from changing their strategy (Nash equilibrium). There are four main types of game theory models:

• -     Static games of complete information: movements are simultaneous and all the players know the payoff functions of the others;
• -     Dynamic games of complete information: movements are sequential and all the players know the payoff functions of the others;
• -    Static games of incomplete information: movements are simultaneous and at least one player does not have complete information about the payoff of the others;
• -    Dynamic games of incomplete information: movements are sequential and at least one player does not have complete information about the payoff of the others.

Another important element of game theory models is the repetition of the games , due to the fact that the strategy of players can change depending on the number of games. In this case we can calculate the net present value of future outcomes, since the nearest payoffs are more valuable than the most distant ones. There is also a series of assumptions when applying these models:

• -          Players are rational;
• -          Players are risk neutral;
• -          Each player acts according to his/her own interest;
• -      When making a decision, each player takes into consideration other players’ reactions.

Static (simultaneous) games are usually represented by payoff boxes, of which the most famous example is the prisoner dilemma. In this case the dominant strategy for both prisoners is to defect, since, in spite of the decision of the other prisoner, for both the decision to defect is the one with the higher payoff.

Prisoner’s Dilemma

On the other side, sequential games are usually represented by decision trees with the payoffs and decisions of the players.

Decision Tree with Players’ Payoff

Some common applications to business are:

• -          Market entry decision making
• -          Price modifications
• -          Quantity modifications

To find the solutions to these games, we use demand, supply, cost, and utility functions. Depending on the possible decisions that the players make, calculating these functions will define the payoff of players to determine the equilibrium of the game. When information is not known, we can use assumptions and weight them with a probability percentage, but this requires the creation of more complex models.

The template that I propose aims at profit maximization based on decisions about price changes. Profits (or payoffs) are calculated by the difference between a cost function and a demand function. The demand is a function of the price elasticity of the market and the cross-price elasticity with other competitors (this information can be gathered through several pricing techniques, for example choice-based conjoint analysis or brand–price trade-off).

More models are available online (Cournot, Bertrand, and Stackelberg games), and there are several Excel templates (for example http://econpapers.repec.org/software/uthexclio/). Data about competitors’ market share, costs, production limits, and so on should be estimated using industry data, published reports, and experts’ opinion (brainstorming, workshops, etc.). Prices can be collected more easily, since they are usually public. Data about price elasticity are calculated through surveys that include questions for price analysis techniques.

TEMPLATE

Download the Game Theory Models Template

23. CONJOINT ANALYSIS

OBJECTIVE

Identify customers and potential customers’ preferences for specific attributes of a product. It can also be used to define the willingness to pay and the market share of different products.

DESCRIPTION

Conjoint analysis is a surveying technique used to identify the preferences of customers or prospective customers. The respondents are shown several products with varying levels of different attributes (e.g. color, performance) and are asked to rank the products. This ranking is then used to calculate the utility of each attribute and product at the individual level. The results can be used to define the best combination of attributes and price or to simulate market share variations with competitors (if competitors’ products are presented).

First of all it is very important to spend enough time designing the analysis, starting with the selection of the most important attributes and attributes’ levels.

There are three kinds of methods:

• -  Decompositional methods: the respondents are presented with different product versions, they rank them, and then the utilities are calculated at the attribute level by decomposing the observations;
• -   Compositional methods: the respondents are asked to rate the different attributes’ levels directly;
• -      Hybrid methods: compositional methods are used in the first phase to present a limited number of product versions in the second phase (they are useful when we have a large combination of attributes and levels).

In addition to the methods described above, several kinds of adaptive conjoint analysis are used to increase the efficiency of conjoint analysis, especially when the number of attributes is large.

In conjoint analyses the price is usually included as an attribute and the price utility is calculated. However, this creates several problems:

• -      By definition the price has no utility but is used in exchange for the sum of attributes’ utilities of the product;
• -     The price ranges, number of levels, and perception of the respondents can bias the answers;
• -    The purchase intention is not included, so we do not know whether the respondent would actually buy the product at the presented price (to avoid this problem partially, the respondents are usually asked to define a limit in the ranking below which products are not purchased).

The willingness to pay is calculated as the exchange rate between price utility and attribute utility. However, to avoid the abovementioned problems, we should consider a different approach, for example dividing the analysis into two phases:

• 1-      Perform a classic conjoint analysis for non-price attributes to define utilities;
• 2-      Ask for the purchase intention of full product profiles with varying prices to define the lower and upper boundaries between which the respondent would agree to purchase the product.

With this information a linear function can be estimated in which the price is the dependent variable and the utility is the independent variable.

In the example we present a classic conjoint analysis that includes the price as an additional attribute. It includes one three-level attribute, one two-level attribute (color), and three levels of price. Full-profile products are presented to the respondents (compositional method), and they are asked to give a preference on a scale from 0 to 10 (10 being the most preferred product) instead of ranking the products.

Combinations and Stated Preferences of Conjoint Analysis

The utility of a respondent is calculated by removing one level for each attribute to perform a multiple linear regression with dummy variables. The removed variables will have a utility of “0,” while the attributes included in the regression will have the utility corresponding to the regression coefficients. After verifying the significance of each attribute (p-value < 0.05; see 38. LINEAR REGRESSION), the coefficients can be summed to build the utility equation.

The utility equation at the individual level can be used to define the most profitable combination of attributes and price. It also allows the building of scenarios in which shifts in the market share are calculated due to changes in the price or products’ attributes compared with the products offered by competitors. Especially for the market share scenarios, it is important to define the purchase intention by asking the respondents to state a “limit” beyond which they will not purchase the product.

In the template a second sheet is presented in which the price is not included as an additional attribute but the respondents are asked about it separately, either directly or by showing them different price–product combinations and asking for their purchase intention. The last example usually performs better, but if we have numerous combinations, we cannot show all of them.

Price–Utility Linear Relation

There are two main approaches when creating surveys for conjoint analysis:

• -     Classic conjoint: the respondents are shown all the combinations of attributes’ levels and are asked either to rank them or to define their preferences on a certain scale (e.g. 0 to 10). If the number of combinations is too large, we should either split the combinations and present them several times to the respondents or present only a certain percentage of all the possible combinations (randomly selected). We should also ask for a “limit,” that is, the ranking position or preference level at which the respondent would change his purchase intention.
• -     Conjoint in which the price is not an attribute: the process is the same as the classic conjoint analysis, but the price is not included as an attribute. After asking the respondents to rank or set their preferences concerning several combinations of attributes’ levels, they are asked whether they would purchase a specific combination at a specific price. Depending on the response, either the utility or the price is modified to identify the WTP. If the number of combinations is limited, each one can be tested; if the number is large, not all combinations can be tested and the WTP must be calculated for different levels of utility and can then be estimated for all the combinations.

TEMPLATE

Download the Conjoint Analysis Template

15. BUSINESS MODEL CANVAS

OBJECTIVE

Analyze our own business model or competitors’ business models.[1]

DESCRIPTION

This tool, invented by Alexander Osterwalder et al.,[2] can be used to analyze how an organization is creating and delivering value to its customers. Even though its original purpose was to help in creating a new product or business, in this book the business model canvas is presented as an analytical tool, since those kinds of models are not covered. This model can also be useful for understanding whether a company is a competitor or not, since it analyzes the value proposition, which responds to customers’ needs. In fact, companies compete not on products but on the needs that they satisfy or the problems that they solve for their customers.

Business Model Canvas

The study includes the analysis of nine building blocks of the business and how they are related to each other. First we define our customer segments and then the value propositions that we are offering to them. The value proposition is a need that we satisfy or a problem that we solve for a specific customer segment. It is possible that we are offering different value propositions to different customers; for example, a search engine is providing search results to web users and advertising spaces to companies. Then we identify how to deliver this value to our customers (channels) and how we manage our relationships with them (customer relationships). At this point we are able to describe our revenue model (revenue streams). However, to understand how to create our value propositions, we need to identify our key activities, key resources, and key partners. These three blocks allow us to identify our cost structure. For more information about this model, visit the official website[3] or sign up for the free online course “How to Build a Startup.”[4]

TEMPLATE

Download the Business Model Canvas Template

---

[1] This is a tool that was used originally for the definition of new products or businesses, but, since the purpose of this book is to provide analytical tools, we use the business model canvas as a model to analyze business strategies.

[2] Alexander Osterwalder, Yves Pigneur, Tim Clark, and Alan Smith, Business Model Generation: A Handbook for Visionaries, Game Changers, and Challengers (John Wiley and Sons, 2010).

[3] http://www.businessmodelgeneration.com/canvas/bmc

[4] https://www.udacity.com/course/how-to-build-a-startup--ep245