How do free-to-play video games make big profits?

Every day, millions of people play World of Tanks to battle other tanks in virtual battlefields – and many of them have never paid a penny to play the game. Still, Wargaming, the developer of World of Tanks, has made billions in the gaming industry.

How did this gaming juggernaut make money from its free-to-play gaming structure and come to see the invaluable value of every customer – even those who don’t pay a penny? In part through the use of analyzes.

The goal of Wargaming is to provide a great experience for players of all levels. Anyone can play for free on Mac, Windows, console or mobile versions, and players who want more can make in-game purchases.

Wargaming’s most-played game, World of Tanks, has 110 million registered users online, and Wargaming collects data on every shooting shot and every move made in each online game. “At any given time every day, we have about 4 million players playing our games,” said Alexander Ryabov, head of Wargaming Business Intelligence Data Services. “They play multiple strokes, and these strokes have multiple events in them, all of which generate close to several terabytes of data daily.”

Wargaming collects data from the other players logging on to a game when they log out. The company also collects and analyzes in-game chat logs along with mentions of its games on social media sites and in many game discussion communities. Using this data, they can run models to retain customers, cross-sell other games, convert players to paid users, monitor player travel, and reduce friction points in the games.

In total, Wargaming processes more than 30 terabytes of data per day. Month. It stores 98 percent of its data in Hadoop on an Oracle Big Data Appliance, where Cloudera manages the Hadoop deployment. Once the data is inside Hadoop, ETL developers create databars that integrate with SAS® to generate models and put them into production.

Improving gameplay and customer offerings with analytics

A team of data scientists at Wargaming develops models whose scores can be sent to an in-game event processing component, to the company’s CRM systems and back to the team for further modeling.

Recently, for example, in the data, the team recognized that players continued to die at a particular location. “So they set up a hill at that spot to balance the map,” Ryabov explains. “Our computer scientists have created a heat map, where you can see on each playing card every shot fired over a certain period of time.”

The team also uses analytics to see if players miss certain elements of the game, allowing the game to send messages for a better experience next time. The message may tell a player where he can access certain weapons or identify translated locations from a previous game.

“It will help players have a better experience in a game next time,” Ryabov says. “This is just one example, but a lot of such things can be achieved by using modeling and putting those models into production.”

To further enhance the customer experience, Wargaming uses text analysis on feedback collected on social media and in direct conversations with customers. “We can place certain filters in social media to get an emotional analysis of the overall game. We can also use emotion analysis for customer support and to identify our all-star players on multiple channels, ”Ryabov says.

Scaling analytics for the massively multiplayer online experience

When Wargaming created its business intelligence program three years ago, it forced open source technologies. “Once we understood the need for in-depth data analysis and data mining, we started doing some initial, advanced analytics modeling in R, Spark, Python and all the other open source solutions,” Ryabov says.

But the team realized that scaling the initial effort to thousands of models and more and more data every day brought great challenges. In describing Wargaming’s early use of open source analysis, Ryabov says: “The biggest problem for us was scalability. Our data scientists come up with a model concept, do some data breaches, some data extraction and then we have to automate the results. It was all manual. It was a lot of work for our developers. “

According to Ryabov, the three models his team created took three to six months to implement. “Once we realized that we were running hundreds or even thousands of models for all our games, all our regions and all our time frames, we started looking for the solution that could make it scalable for us. “

After a thorough investigation, Ryabov and his team found what they needed. “SAS Factory Miner and SAS Model Manager were perfect for our use cases, “he says,” because we can take the same model and multiply it by time frames, regions and with different products. So a model is practically the same, but we can put it in the production environment where we run, maintain and promote it again and again in an industrial way. In our research, SAS was the only viable option. “

After the data has been compiled and the modeling methodology established, Ryabov says multiplying the model into thousands of similar models has become a one-person job. “Manually creating and maintaining that many models would take something like 10 to 20 people, and of course they will make mistakes. An automated production environment like SAS does not make mistakes. “

The benefits of industrialized modeling

Automated and industrialized modeling has created many benefits for Wargaming:

  • Moved most coding to a point-and-click based workflow for model building efficiency.
  • Reduced the amount of time needed to develop and implement models by 60 percent.
  • Reduced the need for data warehouse management in model deployment and automation by 80 percent.

Overall, Wargaming data scientists are able to create and implement more models in less time, which will result in higher revenue, better use of resources and lower opportunity costs. As the market grows and Wargaming continues to diversify into other platforms, it will be able to run even more models, retain more customers, acquire more customers and apply more complex analysis, all within the same analytics platform.

Most importantly, players also benefit. “Our computer scientists are a group of talented people who have very innovative ideas for how to offer players exactly what they want at the right time,” Ryabov says. “And SAS helps to increase overall satisfaction and make the player experience even better.”

In addition, enhancing the gaming experience encourages more players to become long-term customers with a desire to invest in the game. “As our founder, Victor Kislyi, says,” Our goals are ultimately happy players. “If the players are happy, you know everything else is coming.”

Source link