Forecasting in the gaming industry. Part 2: How well do you know your players?
After you have a little understanding of the basics, let's take a closer look at the benefits of forecasting for game developers. Forecasting can be a kind of crystal ball for you, but only if you have the right information. So the first thing you need to do is start collecting data, a lot of data. If you do not have the ability to unload data from the game, things will not happen.
This material is the second part of a series of articles, which deals with the prediction and use of predictive metrics in the gaming industry. If you have not read the previous article on forecasting, it is better to first read it here to get an idea of the predictive analytics, modeling and assessment of reliability.
As soon as the relevant data is at your disposal, it is the turn of the analytics. There are many methods for thorough data analysis, such as analytics based on indicators such as daily active users (DAU), average user revenue (ARPU), and average session duration. The customer value indicator (LTV) is most appropriate for analyzing game data. In general terms, it represents the amount that the user is likely to spend before abandoning the game. Some consider the user's current expenses, but we are more interested in either general or future expenses.
')
The most important thing is to understand which players are most valuable to you. They are all different: for every hardcore player whose LTV is measured in thousands, there are far more users who haven’t invested a penny in the game. And in your interest as a developer - to strive to keep players with a high LTV.
But back to the metrics. LTV is great for getting a general idea of the situation (unless, of course, you have a valid formula). But at the same time, this is a rather superficial way of assessing your audience and its interaction with the game.
If you are developing games, then most likely you are now shaking your head in disapproval. After all, users do not play in a confined space! They interact and communicate with other players, they have clans, guilds, social networks. Does this mean something?
Such data are extremely important for forecasting and are known as social value. Like LTV, social value is also measured in dollars. Try to imagine that inside, for example, Facebook there are thousands of social networks that users create around themselves. These are their friends and friends of friends. The traditional LTV metric involves analyzing each node of the network in order to establish which players are most important to you, while social value is determined by the network entirely and the interaction within it.
Suppose you have a player (let's call him “Player A”), who spends $ 5 in a game, and Player B, who spends a dollar. Whose value is higher? A traditional metric would point to player A. But the analysis reveals that for every dollar spent by player B, player C receives $ 3, another $ 2 from player D, and another 3 from player E.
Add it all up - and you look at player B in a completely different way.
Forecasting is a scientific method, but do not underestimate the importance of human influence. Social value as a parameter takes into account this factor. Add up your LTV and social value and you get the full value of the player. This option combines the best of both approaches. And it will help him to understand which players are most important to you.
It is worth noting that the most valuable players are often not the ones you think about in the first place. Users who spend a lot in the game and who have a high LTV, as a rule, have no influence. And players whose net worth is determined by social connections and LTV spend a little, but have a significant impact on other players and thus trigger a chain reaction. These are the so-called “Whales” (Social Whales), and it is on them that you need to focus on as a target audience.
Therefore, for game developers, the million dollar question (or even more, depending on the game) is: who will quit playing, and how can this be prevented? As you probably guessed, predictive analytics will help answer this question.
Predictive model not only reveals who has already left the game, but also shows who is on the verge of leaving and what losses it threatens. Of course, you cannot stop all users. Here we will need such a parameter as the user churn rate. The calculation of the expected amount of loss is as follows: the total cost of the player is multiplied by the degree of probability of his leaving the game. For example, the total cost of a user named Bob is $ 100, and we are 65% sure that he will leave the game. If we had a thousand of such beans, we could say that, over time, the average loss from the care of any of them would be $ 65. Thus, we attribute this amount to our Bob and generally we are right.
Based on these data, it is already possible to draw conclusions. If the risk that an unremarkable user leaves the game is equal to the average, you can let it go. But what if on the verge of care "whale"? In this case, you need to seriously revise the strategy of retaining the players, because with the departure of the "whale" you will lose, and his entire social network. Think of the expected amount of loss that you will suffer if this happens: in the case of the same Bob, it will be $ 65.
The opposite of user outflow is conversion - the phenomenon when your players start investing money into the game and the project makes a profit. Just the dream of any free games developer. The main analytical programs can identify users who have begun to make in-game purchases, but predictive analytics is capable of more, namely, to predict which players will start to do it and what income it will bring you. If you develop the system correctly, you can also predict which players will become “whales” and whom you should focus on in order to attract other users.
All of the above is by no means a universal guide to predictive analytics, even within the framework of the gaming industry. Over time, the prediction will reach a level where developers can predict the behavior of players in the aspect of virality, monetization, and even reimbursement of advertising costs.
So, what awaits the gaming industry? I will discuss this in the final article in this series.
This material is the second part of a series of articles, which deals with the prediction and use of predictive metrics in the gaming industry. If you have not read the previous article on forecasting, it is better to first read it here to get an idea of the predictive analytics, modeling and assessment of reliability.
As soon as the relevant data is at your disposal, it is the turn of the analytics. There are many methods for thorough data analysis, such as analytics based on indicators such as daily active users (DAU), average user revenue (ARPU), and average session duration. The customer value indicator (LTV) is most appropriate for analyzing game data. In general terms, it represents the amount that the user is likely to spend before abandoning the game. Some consider the user's current expenses, but we are more interested in either general or future expenses.
')
The most important thing is to understand which players are most valuable to you. They are all different: for every hardcore player whose LTV is measured in thousands, there are far more users who haven’t invested a penny in the game. And in your interest as a developer - to strive to keep players with a high LTV.
But back to the metrics. LTV is great for getting a general idea of the situation (unless, of course, you have a valid formula). But at the same time, this is a rather superficial way of assessing your audience and its interaction with the game.
If you are developing games, then most likely you are now shaking your head in disapproval. After all, users do not play in a confined space! They interact and communicate with other players, they have clans, guilds, social networks. Does this mean something?
Such data are extremely important for forecasting and are known as social value. Like LTV, social value is also measured in dollars. Try to imagine that inside, for example, Facebook there are thousands of social networks that users create around themselves. These are their friends and friends of friends. The traditional LTV metric involves analyzing each node of the network in order to establish which players are most important to you, while social value is determined by the network entirely and the interaction within it.
Suppose you have a player (let's call him “Player A”), who spends $ 5 in a game, and Player B, who spends a dollar. Whose value is higher? A traditional metric would point to player A. But the analysis reveals that for every dollar spent by player B, player C receives $ 3, another $ 2 from player D, and another 3 from player E.
Add it all up - and you look at player B in a completely different way.
Forecasting is a scientific method, but do not underestimate the importance of human influence. Social value as a parameter takes into account this factor. Add up your LTV and social value and you get the full value of the player. This option combines the best of both approaches. And it will help him to understand which players are most important to you.
It is worth noting that the most valuable players are often not the ones you think about in the first place. Users who spend a lot in the game and who have a high LTV, as a rule, have no influence. And players whose net worth is determined by social connections and LTV spend a little, but have a significant impact on other players and thus trigger a chain reaction. These are the so-called “Whales” (Social Whales), and it is on them that you need to focus on as a target audience.
Therefore, for game developers, the million dollar question (or even more, depending on the game) is: who will quit playing, and how can this be prevented? As you probably guessed, predictive analytics will help answer this question.
Predictive model not only reveals who has already left the game, but also shows who is on the verge of leaving and what losses it threatens. Of course, you cannot stop all users. Here we will need such a parameter as the user churn rate. The calculation of the expected amount of loss is as follows: the total cost of the player is multiplied by the degree of probability of his leaving the game. For example, the total cost of a user named Bob is $ 100, and we are 65% sure that he will leave the game. If we had a thousand of such beans, we could say that, over time, the average loss from the care of any of them would be $ 65. Thus, we attribute this amount to our Bob and generally we are right.
Based on these data, it is already possible to draw conclusions. If the risk that an unremarkable user leaves the game is equal to the average, you can let it go. But what if on the verge of care "whale"? In this case, you need to seriously revise the strategy of retaining the players, because with the departure of the "whale" you will lose, and his entire social network. Think of the expected amount of loss that you will suffer if this happens: in the case of the same Bob, it will be $ 65.
The opposite of user outflow is conversion - the phenomenon when your players start investing money into the game and the project makes a profit. Just the dream of any free games developer. The main analytical programs can identify users who have begun to make in-game purchases, but predictive analytics is capable of more, namely, to predict which players will start to do it and what income it will bring you. If you develop the system correctly, you can also predict which players will become “whales” and whom you should focus on in order to attract other users.
All of the above is by no means a universal guide to predictive analytics, even within the framework of the gaming industry. Over time, the prediction will reach a level where developers can predict the behavior of players in the aspect of virality, monetization, and even reimbursement of advertising costs.
So, what awaits the gaming industry? I will discuss this in the final article in this series.
Source: https://habr.com/ru/post/270043/
All Articles