Study: Predicting Player Behavior and How Zynga Profits from Data Analysis

An interesting front page story in The Wall Street Journal today by journalist Nick Wingfield discusses how casual gaming giant Zynga cashes in on their millions of players. After developing Fishville, following in the footsteps of highly successful titles like Farmville, managers noted players spending in-game currency on one type of fish more so than others. The “translucent angler fish” was being purchased more than 6 times the rate of other virtual fish. So the company quickly developed a whole line of translucent sea creatures, charging as much as $4 (this time, in real world money) for more exotic varieties.

This formula has been very successful for the company. Although only about five percent of Zynga’s player base spends serious money in their games, so many millions of people play that the company rakes in millions. They rake in even more by figuring out what the players want through data analysis.

Zynga is transforming the game industry. Traditional videogame companies create games they think players will like, then sell them. Zynga offers free games through Facebook Inc.’s social network, then studies data on how its audience plays them. It uses its findings to fiddle with the games to get people to play longer, tell more Facebook friends about them and buy more “virtual goods.” At the heart of the whole process is Zynga’s ability to analyze reams of data on how players are reacting to its games.

“We’re an analytics company masquerading as a games company,” said Ken Rudin, a Zynga vice president in charge of its data-analysis team, in one of a series of interviews with Zynga executives prior to the company’s July filing for an initial public offering.

This formula for financial success has other companies following Zynga’s lead. Rather than spending millions developing a title with a short shelf life, companies are turning to free games with extras that cost money. The primitive graphics Zynga uses are generally derided by serious gamers, but Zynga aims for the mass market, much the way American beer brewers produce bland beverages that appeal to the most palates.

All of Zynga’s games go through what amounts to a giant ongoing lab experiment involving players. Zynga conducts hundreds of “A-B tests” within its games, in which two sets of players see virtual goods on sale with, say, subtle color differences to see which color sells better…

Sizhao Yang, a former Zynga executive who helped create its virtual farming hit “FarmVille,” says his development team figured out by analyzing virtual-goods-sales data that “people buy animals a lot more than tractors and other inanimate objects.” The findings led the “FarmVille” team to more prominently feature animals in its online store, he says.

Interestingly, Wingfield reports there is considerable tension in the company between the data jockeys and the game designers. The game designers have a certain idea of how a game should look and function. The analysts drive the direction of game development based on the data, leading to tension. Some designers have quit the company in protest. Still, data remains the keystone in Zynga’s game plan for the foreseeable future.

The Zynga story on data analysis comes on the heels of the recent International Conference on the Foundations of Digital Games in Bordeaux this summer (fdg2011.org). There, Brent Harrison and David L. Roberts over at North Carolina State delivered an interesting paper, Using sequential observations to model and predict player behavior. Here’s their abstract:

In this paper, we present a data-driven technique for designing models of user behavior. Previously, player models were designed using user surveys, small-scale observation experiments, or knowledge engineering. These methods generally produced semantically meaningful models that were limited in their applicability. To address this, we have developed a purely data-driven methodology for generating player models based on past observations of other players. Our underlying assumption is that we can accurately predict what a player will do in a given situation if we examine enough data from former players that were in similar situations. We have chosen to test our method on achievement data from the MMORPG World of Warcraft. Experiments show that our method greatly outperforms a baseline algorithm in both precision and recall, proving that this method can create accurate player models based solely on observation data.

While not fixating on the profit motives that Zynga has in mind, Harrison and Roberts offer clues to game designers in guiding player behavior in-game. Educational games could become more engaging:

The ability to accurately predict a player’s behavior in a game has a number of applications. While these applications are beyond the scope of this paper, we discuss two of them briefly here to better situate and motivate our approach. With a model of player behavior, we can create an experience that is unique to a user’s tendencies or preferences. For example, if we predict that the user will choose to fight a certain non-player character (NPC) rather than talk to it, that NPC can be made more willing to fight. Another application involves guiding players to parts of games that they may enjoy. Modern games often take place in large, sandbox worlds where the player is given total freedom. It’s quite possible that players may never see content that they would like because the sandbox is just so big. Predictions about a player’s behavior can be used to guide her to the parts of the game that she would enjoy.

Eschewing surveys, the authors recommend a purely data-driven approach (as does Zynga):

We feel that a purely data-driven approach has significant promise for creating accurate predictive models of player behavior in games without the difficulties associated with earlier modeling techniques. Very little research has been done in this area to date.

Read the entire paper for further discussion of the algorithm they developed. Very interesting.

References:

Harrison, B & Roberts, D. L. (2011). Using sequential observations to model and predict player behavior. In Proceedings of the 2011 Foundations of Digital Games Conference. (FDG 2011), Bordeaux, France.

Wingfield, N. (2011, September 9). Virtual products, real profits. The Wall Street Journal, p.A1.
-

Is FarmVille Educational?

This blog has followed social gaming juggernaut Zynga’s progress for a couple years now. One of its most popular gaming apps is FarmVille, which runs on Facebook and touts an estimated 70 million players, making it one of, if not the, most popular games ever. Testaments to the game’s popularity abound. On the radio station I listen to on the way to work, the morning guys brought up the game recently. One complained he introduced his mother to Facebook, and now she spends hours playing FarmVille. Another said he avoids Facebook specifically so he won’t get caught up playing games like FarmVille all day.

Many players have noted the “work” in FarmVille seems somewhat educational. This, in fact, is what intrigues educators about video games in general. They are so interactive and require focused attention to progress. So, the thinking goes, if we can have students play with educational elements perhaps they’ll absorb some pedagogical content in ways they can’t through books or television.

Could FarmVille be a tool leveraged for classroom use? In November I was invited to sit on a panel of school district tech directors at a regional technology conference to discuss the educational value of social networking. One fellow tech director indicated her school board suggested the district open their network to Twitter, Facebook, and other social tools to students as well as staff. She described the various issues involved, how teachers treated the new access as a classroom management issue, and ways in which the tools were being incorporated into the school day. Then, she said the high school Ag teacher was investigating ways to bring FarmVille into the classroom.

So, is FarmVille educational? Can it be used effectively in the classroom to teach useful things? I turned to the net to see what the hive has to say and also try to find some academic research on the issue.



Math and Organization Skills
Like many games, there are things you can count in FarmVille, and a modest amount of math skills might prove helpful in the game. An eHow article offers six steps in using FarmVille to teach math. Here’s a sample:

Teach fractions using the Chicken Coop and Dairy Barn. There are 4 windows in each building and each building can hold 20 animals. For every 5 animals a head pops out a window. So you can show them how 4/20 is 1/5 of the animals.

CommonSenseMedia.org, which purports to rate video games for parents and teachers, notes that FarmVille requires “simple math and organizational skills.” Later in the review author Carla Thornton writes:

The game itself is clean, safe, and loads of fun, if not especially educational. In FarmVille players plow, plant, and harvest crops to earn virtual coins, raise animals and improve their farmsteads with fences, windmills, and other objects. The more Facebook friends a player can convince to become FarmVille neighbors, the bigger and more successful the farm will be.

Lisa Russell, writing over at the home schooling section for Suite101.com, shows how players can exert a little more math effort to figure out the fastest way to earn money in the game:

Initially, the only seeds available are strawberries, eggplant, wheat and soybeans. Strawberries cost 10 coins and after 4 hours are harvested for 35 coins, a ROI (return on investment) of 25 coins, or 6.25 coins an hour. Using the same method of calculation, it can be seen that the eggplant is worth only 1.31 coins per hour, the wheat breaks down to only 1.1 coins per hour and finally, the soybeans are worth 2 coins per hour. Clearly, the strawberries are a better investment for the player who has time to return in 4 hours to harvest.

Later, she offers a formula for the calculation:

H=harvest value

C=initial price

T=time (in hours)

ROI=(H-C)/T

Players can use a similar formula for comparing the value of their trees (both purchased and gifted) as well as their animals. … FarmVille may have absolutely nothing to offer on a scientific level. In fact, if an entire generation of humans were to learn farming skills from this game, humans might starve to death. However, for math skills and virtual applications of algebra, as well as estimation and strategic planning, FarmVille is more than just fun and games.

So the general consensus seems to be, FarmVille requires a little math skill and some attention to organizational details, but it was made more for fun than education, as are so many popular games.



Academic Interest
As far as academic consensus, a lot of the research interest in FarmVille has revolved around the game indirectly. It crops up in lists of popular social games in academic papers, for instance, but specific studies focusing on the game itself are rare if not non-existent.

A great example of FarmVille serving as a framework for a presentation is one loaded onto Slideshare.net by Sidneyeve Matrix over at Queen’s University in Kingston, Ontario. It is titled Pedagogy Inspired by FarmVille, or Seeds of Engagement, From Social Games to the Classroom: Educational Design Inspired by FarmVille.

In it, she highlights three videogame design principals that can be extrapolated for classroom courses. They are derived from a discussion at the recent Social Games Seattle meeting led by Amitt Mahajan, who is part of the core team and lead designer for FarmVille.

First, instructors should design games with broad appeal. FarmVille succeeds because playing farm is something many kids have grown up doing, sometimes using plastic toys provided by companies like PlaySkool. In the classroom or lecture hall, Dr. Matrix suggests this can translate to humanized case studies, current events, and pop cultural references to widen the appeal of the subject matter to apathetic students.

Second, FarmVille uses something Mahajan called “microsociality,” meaning social connections become painless. Players don’t have to go out of their way to keep up with contacts; they’re all easily accessible in the game. This has become “a viable alternative to offline face-to-facetime,” according to Dr. Matrix. So, for classroom incorporation she suggests instructors build or use existing social sites where students can share and divide workloads and resources.

Finally, FarmVille succeeds because it adds “visual pleasure.” There is a certain graphic appeal to the game, common among most successful commercial titles, that enhances player engagement. Instructors should be sure and incorporate visually appealing graphics in lectures and discussions to help focus attention on the subject matter.

Conclusion
All told, FarmVille is a major hit, sure to be popular for years to come. Educators, as well as perhaps classroom students, can certainly learn a thing or two from the game. But, ultimately, it was designed more for fun than for teaching essential knowledge.