At the first FinMachine Forum held on Friday, Maxim Eremenko, Director of the Risk Modeling Department at Sberbank, and Andrey Chertok, Head of R&D in Data Science, spoke about how, among other things, the largest bank in the country uses machine learning to generate claims and find business partners for its clients.

Case 1. Smart tips: generation based on the analysis of customer card transactions
Maxim Eremenko: On this moment we have come close to the problem of detection and subsequent prediction of patterns of behavior of cardholders. By analyzing the activity of cardholders, we have learned to identify these patterns.

Andrey Chertok: As part of our participation in one of the bank's projects, we detect behavior patterns of the bank's customers based on its transactions. The first models were associated with descriptive analysis of transactional behavior. For example, the client did not have purchases related to cars - they appeared. This means that he bought a car, and now you can, for example, offer such a client products or services that are useful for car owners.

The next task is to predict certain events, including the very fact of a purchase. In addition to patterns, with the advent of certain MCC codes, it becomes possible to extract enough interesting stories, including those related to the savings activities of cardholders. That is, we see which of the bank's customers are saving money and we prevent certain large purchases. This can greatly enhance the models. The bank can give a wider range of offers. However, this means that such models must constantly adapt.

On the slide, we see three fairly understandable cases: buying a car, repairing an apartment / buying furniture, and the cost of treatment. It is especially valuable if feedback on the products offered to him is possible from the client. Therefore, it is necessary to make models that can take this feedback into account. In many ways, this is the same principle that underlies the reinforcement learning models that we are now starting to develop.

Reinforcement learning or reinforcement learning, which is now being developed, including OpenAI and DeepMind, is a harbinger of AI as they want to see it. No model of the world is put into the system in advance, and the system actually knows nothing about it. The system begins to interact with the world, to receive feedback, the so-called rewards. The system then adjusts its behavior based on how good or bad the rewards are. In the case of banking products, reward is, for example, how interesting or uninteresting for customers this or that offer of the bank turns out to be.

By using methods with specific reinforcement learning properties, we can adapt these algorithms in real time. Of the new approaches, it can also be noted that just recently an article by the same DeepMind was published in Nature, where they talk about how Turing machine elements were introduced into the neural network. As a result, the neural network got the opportunity to have memory, which neural networks lack at this stage.

Case 2. Sales funnel optimization
Andrey Chertok: In this case, we analyze transactional activity, looking for clusters of clients with certain behavior patterns. But in this case we do not associate them with the prediction of any events. For example, we can find customers who frequently fly, travel abroad and convert currencies frequently. Based on this, we make offers to such customers more efficiently.

The slides show what patterns we can find and what products we can offer in this case. In general, an understandable story - certain methods related to clustering are assumed here. Data projection, for example.

Case 3. Cash circulation optimization
Andrey Chertok: Sberbank has a wide network of ATMs, branches, and a scheme for working with corporate clients. Accordingly, the problem arises to predict tomorrow's demand for cash. The more accurately we make this forecast, the more accurate, let's say, we will be able to distribute this money. On the one hand, it is important that the money does not lie idle in ATMs, but instead we can place it on a short-term deposit. On the other hand, we strive to avoid reputational losses - the money runs out earlier than planned, and the ATM stops working, and the client remains dissatisfied.

Here we need models that can work with asymmetric errors. The first models are very simple and are based on classical time series analysis methods related to their smoothing. Now more accurate approaches are required and machine learning methods are already being actively used. Naturally, such methods should be adaptive, since demand depends both on macroeconomic factors and on parameters such as the location of ATMs in the city and the weather forecast. Combining dissimilar features gives a more significant result than using other machine learning models.

Case 4. Modeling the probability of default for a small business in real time
Maxim Eremenko: In 2014 everyone was talking about Big Data. In 2015, machine learning became disruptive and on the edge. Deep learning was the main trend this year. Next year, obviously, they will talk about reinforcement learning.

Unlike the previous three trends, reinforcement learning is easy to try on open platforms. Open artificial intelligence, funded by Elon Musk, and the DeepMind platform are trained on computer games using an open API that allows you to get into the game code.

We get a battle of two algorithms. If in the 80-90s we played Pac-Man, now the machine controls it and this algorithm can be modified. DeepMind took this path a little further and, together with Blizzard, built an algorithm for StarCraft.

Algorithms are trained in such a way as to rationalize them for applied tasks. In the future, they can be effectively set on tasks related, for example, to the translation of textual information into vectors.

Such tasks are the basis of the Google Word2vec engine, which translates from text information into a vector, searches and all the semantic analysis of the text on which it is based.

But the case itself is a bit different. We reviewed active B2B and B2C clients in our portfolio, with a particular focus on small businesses actively exchanging payments. And when working with them, they tried to abandon the classic credit scoring, from the analysis of financial statements and the conduct of a qualitative examination of risks regarding the reputation of the beneficiary, managers, and similar parameters. Instead, we started using some kind of aggregated metric based solely on transactions - in fact, doing analytical scoring based on the data available to the bank.

As a result, it turned out that the model based on credit scoring, which ranks customers according to the probability of default, practically does not differ from classical models in terms of the quantitative metric of accuracy. Her Gini is almost the same at the level of 60-65%. But if the bank's own information is enriched with external data, say, from social networks and used for ranking, then accuracy can be further improved.

In practice, this means that there is no need to spend time assessing risks in terms of classical analysis. You can process the data that is in the system and get a statistically equally relevant quality metric.

Such a model can now only be used to form a list of pre-approved proposals. If the client says, “OK, I agree,” then the process is more complicated. Over time, if we see that the quality of the stream was maintained at the current level or higher, and the model shows more predictive accuracy, then it can be used as some kind of alternative.

Case 5. Natural Language Processing algorithms for the analysis and generation of claims
Maxim Eremenko: As part of the use of text processing tools or Natural Language Processing, we encountered the fact that Sberbank spends a fairly large amount of human and time resources on analyzing claims and preparing a response. At the same time, the analysis of most of the information of the plaintiffs, and the statements of claim against Sberbank themselves, can be automated. Do not use the labor of people who drive in information about passport data in the operative part statement of claim, but you can extract all this: date of birth, passport data, details and the operative part. At the second stage, to prepare the response part of the claims, we suggested using a certain template as an optimization.

Case 6. DefinitionB2B- andB2B-chains
Maxim Eremenko: For active B2B users, you can do not only assess credit risk, but also select typical patterns of his partner. If we see companies with a similar profile in the portfolio economic activity, while both belong to approximately the same cohort, that is, these are not large investment and small businesses, then we, based on these patterns, select partners and recommend which relationships may be of interest to them.

Case 7. Algorithms for @SberbankML_Bot chatbot
Maxim Eremenko: Our chatbot is still learning, but it also performs some things that many people already know how to do, for example, forwarding through the API to open sources like Wikipedia. If you ask him who Gref or Putin is, he will answer.

We have an internal commitment to our bosses that by the summer of 2017, the bot will be able to carry on a conversation about banking, plus it will have basic cognitive abilities and will be able to communicate on abstract topics. At the moment, the bot is based in Telegram, but we are already developing our own messenger [where it will be moved].

Case 8. Our algorithms can not only learn themselves, but also write poetry
Maxim Eremenko: This is more of an entertainment project. We took a recurrent neural network based on the poems of Pushkin, Lermontov and a little on the Jira chat of the developers themselves, and trained the system to write poetry. At first, she did not cope well even with iambic tetrameter, but then even rhyme began to appear. Now he manages to write poetry even about Sberbank.

In this article, I will share with you our experience in solving an interesting analytical task using non-standard visual tools. The article will be of interest to people involved in data analysis, as well as bank managers who specialize in monitoring and analyzing the bank's loan portfolio.

The application, about which, in fact, I will write below, is based on the iDVP platform (Interactive Data Visualization Platform).

So, let's begin!

The problem we were solving and which I am going to describe in this article was formulated as follows:

The bank issues loans to large legal entities- borrowers. The number of large borrowers at one time does not exceed 1,000. Bank management a convenient tool is needed with which one could see (monitor) a complete picture of the bank's loan portfolio. At the same time, it should be possible to move from looking at the loan portfolio as a whole to detailed information on each of the borrowers.

In what conditions is the leader and what does he need?

1. The management wants to spend a minimum of effort on working with the application, interpreting visual information, and analyzing data.
2. The management wants to see the status of the loan portfolio immediately by simply opening the application without making a single click of the mouse.
3. Information should be presented "as much as possible" - on one screen, without the need for scrolling. Already on the first screen, the user should see which borrowers are "problem", how "problem" they are, and what is their share in the portfolio in quantitative and value terms.
4. Tools for filtering and grouping data should be convenient and intuitive.
5. Application screens must be “beautiful” so that management can use it to “spectacularly” present their reports to founders and shareholders.

Bank analysts, as well as vendors of BI tools, are trying to create solutions that would meet all the specified requirements, but not all requirements can be fully met, and as a result, the created software solutions are not always liked by the management. We decided to go our own way and design a solution that would meet all requirements with the highest possible quality.

I already talked about our approach to data analysis tasks in a previous article, if you wish, you can read it.

The main theses of this article

1. When examining a customer, we always try to identify the pain (problem) of the customer, which can be solved with the help of data analysis. And we create an application that completely solves this problem.
2. For data analysis, we do not use "ordinary" BI reports, but three-dimensional applications. In these applications, the visualization of analytical information is performed in the form of 3D objects combined into thematic interactive scenes (screen forms) interconnected by logical transitions.
3. The solutions we create are based on three principles:

• A visual representation of the customer's business picture. Already at the first acquaintance with the application, on the first screen, the user should see all the parts of his business that interest him.
• Uncovering the causes of the problem. Having selected a problem point, the user should be able to use the drill down function, which allows you to go deeper into the problem area, and see the causes of problems on the following screen forms.
• technical aesthetics. The application should cause a wow effect, i.e. should be attractive, intuitive and user-friendly.

These principles, in our opinion, should take an equal position in the formation of requirements for a solution, along with functional requirements.
It was in accordance with the above theses of the last article that we started to create our solution.

Let me remind you of our stages of application design:

1. Setting the task and starting work;
2. Survey of the customer and work with open sources;
3. Analysis, formation of requirements and documentation;
4. Formation of the final document "Application Description".

The following description is structured according to these steps.

Setting the task and getting started

As part of this stage, together with the bank's specialists, we determined that the main "pain" of the customer is to track the state of the loan portfolio, while it should be possible to drill down to a specific borrower.

Naturally, the application must meet all the specific requirements of the bank's management listed above.

Survey of the customer and work with open sources

In the course of the survey, the following picture of this direction of the bank's business was obtained.

The main income of most banks is to provide loans to companies and individuals.

Some banks specialize in lending to the population, others in lending to legal entities.

In this bank, the task of monitoring loans issued to large borrowing companies was especially acute. Borrowing companies belong to different industries, therefore, a portfolio analysis is required both by company and by industry.

The bank compiles and constantly updates its profile for each borrower, which contains information about the reliability of the borrower, about his financial indicators.

Bank analysts also collect information about the movement Money(cash flow) of the borrower and other indicators, build cash flow models. Information is collected from several information systems jar.

Based on the analysis of the collected information, the borrower’s problems are identified and the borrower is assigned to one of the 5 “problem areas” used in the bank to group borrowers:

1. Green zone - this zone includes a borrower who has not identified problems that may affect the repayment of the loan;
2. Yellow zone - the borrower has some problems;
3. Red zone - the borrower has significant problems;
4. Black zone - the borrower with a probability close to 100 percent will not repay the loan;
5. White zone - the borrower's problem has not yet been calculated.

Depending on the problematic nature of the borrower, the bank is obliged to place reserves on special accounts for possible losses, the amount of which depends on the amount of the loan and the reliability of the borrower. In this regard, it is necessary to control the size of these reserves and prevent their growth, because. A reserve is money that is “dead” for a bank and cannot be used.

The bank's analysts also analyze the borrower's overdue debt (NPL - Non-performing loans). Based on the results of the analysis, the borrower is assigned to one of the 4 NPL zones:

1. Green zone - payments on the loan by the borrower are not overdue or overdue for up to 4 days;
2. Yellow zone - delay is from 5 to 29 days;
3. Red zone - from 30 to 89 days;
4. Black zone - from 90 days and above.

As a result of considering all indicators of the borrower, the bank calculates its overall rating, which shows how reliable this borrower is.

For each loan, the timeliness of payments and the fulfillment of other conditions of the loan agreement are monitored.

In the event of a delay in the next payment, the bank finds out the reasons for the delay and takes action against the borrowing company. These may be fines or tightening the terms of the loan agreement.

IN loan agreements"covenants" are also indicated - these are special terms of the contract that prohibit the borrowing company from taking actions that adversely affect the borrower's ability to repay the loan. Examples of covenants are: the obligation of the borrower to provide the bank with financial statements, closing accounts in other banks, a ban on obtaining loans from other banks, providing collateral for a loan.

Analysis, requirements generation and documentation

The main functions of the application, providing monitoring of this subject area, were: control of the volume of loans, reliability or problematic borrowers, as well as other indicators.

The more "bad" loans in terms of money the bank has, the worse the quality of the loan portfolio. Therefore, bank management needs to immediately see "bad" loans and "bad" borrowers, be able to see the detailed situation of the problem borrower and decide on further actions in relation to him.

We decided that the work of the user-manager with the application should ultimately be similar to the game "find a problem borrower and find out what his problem is."

Also, to make the application convenient for the bank's management, we decided to make not only a desktop version for Windows, but also for Mac OS, iOS and Android. Moreover, the platform on which we develop these applications allows you to do this, as they say, “with one touch”.

Based on the results of the analysis, the following indicators were identified that need to be monitored for each borrower:

1. Volume of debt
2. Problem zone
3. NPL zone
4. Reserve amount
5. Borrower rating

The application must allow the user to:

1. See all borrowers on one screen; at the same time, it must be remembered that at the same time the bank serves up to 1000 large borrowers;
2. Filter borrowers by the amount of debt;
3. Filter borrowers by problem areas;
4. Filter borrowers by NPL zones;
5. Filter borrowers by bank branches that issued loans to them;
6. Filter borrowers by industry;
7. Filter borrowers by the problems identified with them.

Try to imagine a report (or several reports) that will meet these requirements, as well as the requirements indicated at the very beginning of the article. Represented? And now I suggest you familiarize yourself with our solution.

As I said above, the convenience and beauty of the application is very important for us. great importance. Therefore, not only analysts are involved in working on application screens, but also 3D designers and usability specialists.

As a result, we got the following main screen of the iDVP.Banks.Credit Processes application (see the figure below).

At first glance, the screen seems quite saturated, but at the same time, all the information is divided into zones, which makes it easier to perceive. What zones did you end up with?

Bank borrowers are represented in this zone in the form of multicolored planets (balls). The size of the planet corresponds to the amount of debt on the loan from this borrower. The color of the planet corresponds to the problem area of ​​the borrower. At the same time, borrowers of the same color are grouped together so that it is possible to visually assess their share (quantitatively and by the amount of debt) in the loan portfolio. Thus, we solved the problem of "seeing all borrowers on one screen."

In the same zone there is a filter by the size of the planets (pay attention to the scale and the circle located to the right of the planets). With this filter, you can specify the minimum and maximum amount of debt for the displayed borrowers. You can leave on the screen only large borrowers, for example. The task of “filtering borrowers by the amount of debt” has been solved.

When you click on any planet, you go to the "Borrower's card" screen (see the picture below), it provides detailed information on the indicators characterizing this borrower and his loan.

The task of "transition from the overall picture of the loan portfolio to a specific borrower" to analyze the situation should be carried out with a minimum number of clicks" has been solved.

In the initial state of the screen of a small planet, it is not always convenient to click - it is simply difficult to hit them with the mouse or, in the case of touch-interfaces, with a finger. To compensate for this difficulty, in the central zone it is possible to zoom in and out (zoom-in and zoom-out) of any part of the planetary system. This is done either with the mouse wheel or, if a touch screen is used, with the "pinch" action.

This zone contains a filter by color zones of problematic borrowers. You can click/unclick the necessary/unnecessary areas of problematic areas. As a result, only planets-borrowers of the colors desired by the user will remain in the central zone. The task of “filtering borrowers by problem areas”, “filtering borrowers by NPL zones” has been solved. An attentive reader will surely ask how we filter borrowers by NPL zones using this tool, because it only filters problem areas. It's simple: in the upper left part of the screen there is the text "RESIDUE DEBT" - this is, in fact, a drop-down list for selecting borrower display modes. The following modes are available for selection:

1. DEBT RESIDUE - in this mode, the size of the planets is determined by the amount of debt, and the color of the planets is determined by the problem area;
2. NPL VOLUME - in this mode, the size of the planets is determined by the amount of overdue debt, and the color of the planets is determined by the NPL zone;
3. RESERVE - in this mode, the size of the planets is determined by the size of the reserve, and the color of the planets is determined by the problem area;
4. RATING - in this mode, the size of the planets is determined by the rating value, and the color of the planets is determined by the problem zone.

Here, in the “NPL Volume” mode, the filter on the left becomes the NPL color zone filter.

Filter zone on the right

This zone contains the "accordion" filtering element, which contains three filters:

1. CA + TB (central office + territorial banks) - using this filter, you can leave on the screen only borrowers whose loans were issued by the central office (head office of the bank) or territorial banks (branches).
2. INDUSTRIES - allows you to filter borrowers of certain industries.
3. PROBLEMS - this filter allows you to leave on the screen only those borrowers for whom the bank's analysts have identified certain problems.

A feature of the "accordion" element is that only one filter is deployed at a time (the "PROBLEM" filter is deployed in the sketch). The rest of the filters are in a collapsed state.

The task of “filtering borrowers by bank branches, by industry, by problems” has been solved.

Lower Graph Zone

This zone contains a graph that displays the change in the ratio of problem areas or NPL zones over time. To do this, use the type of graph "line chart with accumulation". The colors of the graph correspond to problem areas or NPL zones.

The user has the ability to set the slider to any date on the chart, and only those borrowers that the bank had at that time will be displayed in the central zone. The sizes of the planets and their colors will correspond to the amount of debt and the problem area that each borrower had on the selected date.

Below I attach the rest of the application screens: thumbnails and titles. And you will have the opportunity to study them, analyze them yourself. If you have any questions about the content - ask them in the comments, I will definitely answer.

The main screen with the display of a pie chart of the distribution of problematic color zones

The main screen with borrowers filtered by the amount of debt (on the scale to the left of the planets, the lower display limit is set at 20% of the maximum)

Main screen. Approach of planets (zoom-in)

Borrower card

The financial simulator helps people to look at the work of the bank from the inside

To bookmarks

Representatives of the Home Credit bank told the site how the company developed the online game "Your own banker", which allows players to feel like a bank director. Thanks to the simulator, the audience can understand how exactly the financial institution works, which allows them to be involved in the brand.

The idea to develop an online financial game came to the bank in 2015. The company set itself the goal of getting people interested in banking, involving them in the brand, and in a playful way telling about the basic principles of the bank.

“Experience shows that people are more willing to interact with what they understand. And our game gives people the opportunity to look at the bank from the inside: the players themselves determine how “their” bank would work, and then the system automatically calculates profit or loss,” says Maria Burak, director of the Marketing and Marketing Communications Department at Home Credit Bank.

Bank management is divided into nine areas (loan products, risks, customer service, and so on). By choosing a menu item, the player must either answer a question or set the values ​​of financial indicators.

After the user determines the policy of the organization, the system will calculate how successful the bank will be and how much the player will be able to earn (or lose).

The game launched in mid-2016. Since its opening, more than 32,000 people have participated in it. “Initially, we expected that by the end of 2016 at least 10,000 people would play the game. As a result, we exceeded our initial plans by more than three times,” notes Burak.

According to the Director of Marketing, about 20% of the players played several times, trying to improve their result. The audience consisted of the bank's clients, subscribers of its groups in social networks, people who came through the repost of other players, as well as bank employees.

“The online game has no prize pool and the company did not pay for promotion. Players were attracted through the website and the official communities of the bank in social networks. We also made a mailing list with an offer to play "Your own banker" to customers and employees of our bank, ”she notes.

According to Burak, in this way the bank solves several important tasks at once: it attracts interest in the brand, raises awareness and financial literacy of players, and also involves them in the gaming process.

Maria BurakDirector of Marketing and Marketing Communications Department of Home Credit Bank

We did not have the task of advertising the bank's products. We wanted to change people's attitude to the banking business in general - to talk about the goals and objectives, to explain how banks achieve their results. This is more about the image side of the issue than product sales.

The idea, the model, the visual concept of the game - everything was thought up and developed inside the bank. The involved agency only drew and programmed the quest. The prototype for creating an online quest was a training board game, also created by our bank employees.

It is also called "Your own banker." Its game mechanics are much more complicated: you need to play in teams in several rounds. The full passage of the training board game takes from several hours to a whole day. In the online version, you can achieve results much faster: in a few minutes. It is worth noting that we do not promote the products of Home Credit Bank in any way inside the game.

By the way, during the existence of the game, she also had her own record holders. The game can be played an unlimited number of times. One person played 127 times, received both profit and loss. He set an absolute record - 42,209,768,000 rubles, which has not yet been broken, although several people were able to get close to him and "earned" 42,135,451,000 rubles.

Promotion of banking products and formation of demand for them.

Gamification is one of the most popular marketing trends at the moment. And it was logical for us, as a bank with an active and advanced audience, to support it by offering customers a promotion where the game mechanics are implemented at the proper technological level and are largely personalized.

— Kirill Bobrov, Vice President of Tinkoff Bank for Customer Acquisition

As a result, many users get the first experience of earning interest on money that is simply in the bank. Clients understand from their own experience that a savings account is a simple and profitable product. And this is the first step to opening a deposit or a deposit, and to expanding the idea of ​​banking products in general.

An indirect result is also the regular use of the online bank by the user, since only there you can see your progress.

Moreover, the result is achieved indirectly with the help of game mechanics, it is presented in the form of a story about an active lifestyle, which is much more interesting for a certain audience than the ability to save and receive interest (this is offered by any bank) or a call to use an online bank.

Gamification is a super topic. It's all about involvement. It is boring to make transactions in a bank, it is boring to use banking products. And people love to compete, people love to compete. It sits inside and very deep. And you can exploit these qualities of people. How to do it in a bank? Cases are few. But my deep conviction is that those who learn to actively engage their customers, including using gamification, can earn a lot of money.

— Ivan Pyatkov, Director of Remote Service and Sales Department, Bank of Moscow

Increasing the financial literacy of users to simplify the perception of complex banking products: deposits, investments, etc.

Typical approaches:

1. Loyalty programs with points, miles and cashback as rewards.
2. Interactive contextual learning for new features. Wellcome scripts.
3. Quests and contests for clients.
4. Creation of simple useful services with elements of the game: PFM, accumulation on the target.
5. Viral promo games that announce new products in an entertaining way.

The game makes any process easier and more fun. That is why more and more applications based on gamification appear. In the game, users gain new knowledge, develop good habits, or, conversely, get rid of bad ones.

Why do banks and payment systems need gamification?

"Gamification" is, in fact, a system of motivation and incentives. IN Soviet time there was a board of honor on which photos of the best employees were placed (there was no talk of stimulating buyers at that time). Now there are many more opportunities to make the motivation system interesting, exciting, non-linear. It is its transformation into a game that is gamification.

Gamification is designed to captivate the user, the person will strive for new achievements. It is important that this path is clear. For example, the user not only gets new status in the application, but sees movement towards it, understands what he must do for this. All this with beautiful graphics.

The human brain always strives for simplification. Therefore, we quickly take on things that are clear to us, and put off the difficult ones for later. Gamification is one way to simplify, reduce discomfort.

Who can you play with?

Brain activity does not depend on social role. Therefore, gamification works with both customers and employees. Now more and more generation Y specialists are coming to the company. For them, a signed contract is not the most significant reason for selfless work, and financial incentives do not always include full motivation.

Work should be exciting, employees want development and independence. Therefore, the game can start already when an employee is hired and can be used to increase motivation in the future.

And, of course, gamification helps build relationships with customers, increase their loyalty, and form the habit of using a particular service or product. It is in the game that the user can be unobtrusively led to the target action. We will focus on this audience, and in relation to the financial sector.

For many years it was believed that banks and financial institutions you need to create and maintain the image of serious companies, they categorically do not allow jokes. Only in this case, customers will trust them with their money. But the situation has changed: financiers also use gamification.

Goals of gamification

1. Attract new users

It's one thing when you talk about the benefits of a product and quite another when you invite a user to take part in the game.

case

Last year, Rocketbank conducted an online quest with references to the USSR. Users could win an iPhone 7, Spanish jamon or French macaroon sweets. Participants had to complete 12 tasks, for which points are awarded and stamps are placed in a virtual coupon. Some of them were related to the dissemination of information about Rocketbank in in social networks. And one of the tasks - "Party ticket" - involved filing an application for the issuance of a Rocketbank card.

Thus, the participants of the quest, while playing, themselves increased the bank's recognition, expanded its audience and, in the meantime, became customers.

2. Help understand the product

Financial products are often quite complex, the user needs both to explain the service itself and to give instructions on how to use it.

case

The Netherlands-based Robobank brought a game element to the rather complex and confusing process of obtaining a mortgage loan. To do this, the borrower needs to go through the path, specific steps are defined for him, and only after they are completed, the next level opens and the new action icon is activated.

3. Increasing financial literacy

Many banking and payment services not only make sure that customers know their product, but also improve their financial literacy. Frequently, questions about fraud protection and financial decision making are used in gamification.

case

America has a SaveUp reward program. Users are encouraged to act correctly and effectively in relation to finances. Moreover, this is not a loyalty program of any particular bank, it includes users of more than 180,000 American financial institutions.

Points, for example, are counted when a user deposits funds into a retirement account or deposit, repays debt on mortgages, credit cards and other types of loans. In addition, consumers take part in financial education courses on the SaveUp resource. Points can be redeemed for a chance to win prizes.

4. Increase user activity and offer new services

People do not go to the payment service out of boredom or simply because they have a free minute. You need to pay - the user opens the application, makes a payment and leaves. But with this approach, the client may not even know all the features of the service. For example, he realized that it is convenient to pay for utility bills, he comes once a month and makes a payment. Until the HOA or the Criminal Code issues the next receipt, the user may not return to the service.

case

The payment system "Central Cashier" has a large group of users, different from other audiences - taxi drivers. They receive payment from passengers who paid bank card, to an electronic wallet. Some of them simply transferred the received money to their cards. On this interaction with payment system ended.

Therefore, the challenge for business: teach taxi drivers how to use the application to pay for services. To do this, the game was launched. Taxi drivers accepted payment for trips, received bonuses and paid for dispatcher services without commission.

Another case

Alfa-Bank launched the Alfa Activity service. The bank offered users to automatically transfer money to the "piggy bank" in proportion to the steps taken. To do this, it was necessary to link the fitness tracker account with the Internet bank. The results were displayed on a special scale so that the user could understand what he had already saved up for.

And one more

The American bank PNC did not come up with a long and difficult quest. It's just that a piggy bank appears on the screen of a user who is in the Internet bank. When you click on it, the funds are transferred to the savings account. Moreover, the client sets the frequency and amount of payments independently.

5. Loyalty program

We open the wallet and what do we see? A large number of discount cards, many no longer carry them all with them. Therefore, the usual loyalty program does not surprise anyone. Users often even refuse to join it.

case

Gamification will help to revive the bonus program again. Spanish bank BBVA has launched the BBVA Game online service. The customer earns points for completing certain activities, such as making online payments. Points can be exchanged for prizes, pay for music and videos on the BBVA partner site. In addition to points, the user receives medals ("badges"), which are displayed on his profile page.

But it is important to remember that a business should not just launch a game for the sake of the game itself. The purpose of gamification is to make it more interesting to interact with companies, purchase their services and use their functionality. Only in this case, the game will help achieve business goals and increase loyalty.