Data Found About Steam - What's your Game?

Posted on May 16, 2017

The skills the authors demonstrated here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.

Video game is becoming a major force in the entertainment business. According to a 2016 data estimation by PwC, video game sales is projected to grow 5% per year through 2020 reaching an all-time high of $90.1 Billion, especially for PC games. PC gaming is expected to grow at an annual rate of 6.3% higher than any other platforms.

The growth is in part due to the increase in digital sales. Gamers are purchasing games through digital distribution platforms that provides immediate access. Steam is the largest PC gaming digital distribution platform in the U.S. with over 6 Million active users. Additionally, Steam provides services in cloud saving, multiplayer gaming, and social networking. Currently, Steam hosts over 60,000 free and paid games. In this blog, I would like to examine some of the characteristics associated with higher number of players among the top selling games.

Game Data from Steam and

A combination of Scrapy and Selenium was used to extract data. Only games that were in the top sellers were included in the current analysis.

Below you will find a basic layout of the Steam game page. Game specifications, such as developer-defined genres, user-defined keywords, and downloadable content were included in these pages.

Below you will find a basic layout of the Steam game page. Game specifications, such as developer-defined genres, user-defined keywords, and downloadable content were included in these pages.

Lastly, data relating to number of users was extracted from, a third-party website providing real time stats and sales information. The all-time peak number of player indicates the highest number of players that have ever played the game.

The initial dataset included downloadable content as well as soundtracks, and these records were merged with their original items. Numeric columns included:

  1. Price
  2. Number of players
  3. Released year
  4. No of downloadable content
  5. Number of reviews and average rating

Categorical columns included:

  1. Genres
  2. User defined keywords


  • Number of players:


The number of players varied greatly. There are a few mega games, such as Fallout 4 or Grand Theft Auto V, that have more than 300,000 players. However, majority of the games in the top sellers have limited number of players. Roughly 1/3 of the games have less than 100 players and the median is 229 players.




  • Released years and pricing:


Most of the games were released in 2016 and 2017. The top sellers list is volatile towards current sales. For example, multiple Star Wars entries appeared in the top 20 around May 4th due to a significant price cut. In addition, retro gaming, re-releasing games from older PC or consoles, is trendy and Steam includes games dated back to 1987. The game prices range widely from $0.99 to $399. The median price is $9.99. Released years and pricing are not correlated with number of players.


  • Downloadable Content:


Downloadable content (DLC), similar to expansion packs, provides additional objectives, areas, and stories for a released game. Roughly 18% of the games (456) had at least one downloadable content, and DLC availability is associated with a significant increase in number of players.




  • Genres:

Game genres are determined based on the gameplay interaction, and each game can belong to multiple genres. For example, Shovel Knight: Treasure Trove, a popular retro side-scrolling game, is classified into action, adventure and indie. For top sellers, the top genres are indie, action, adventure, and strategy. Despite a growing interest in indie and casual games, indie and casual genres are associated with decreases in the numbers of players on Steam. More than half of the top sellers were indie games, and this might reflect a variety of quality and popularity.


  • Keywords:

Unlike genres, keywords are generated by Steam users, and often reveal additional details beyond the genres. A total of 330 different keywords were used in the dataset, for example, great soundtrack, story rich, and female protagonist. The keywords, great soundtrack, atmospheric, and story rich, are highly correlated with each other.

The combination usage might reflect an immersive experience that are highly desirable by the gamers, and these keywords are associated with a significant increase in the number of players. In addition, open world and sandbox describe games that deviate from the traditional linear structure that grant players more freedom to explore. These games, such as Minecraft, have gained significant traction, and is associated with a higher number of players in the current analysis.


  • Conclusion:
  1. DLC might be a viable tool for developers to continue engage players, and extend the shelf-life of a game.
  2. Several important patterns have emerged in the user-defined keywords that might reflect the current trends in gaming, such as game immersion.

Future analysis is needed to gain additional insight into gamer behaviors and game mechanics. Future studies should focus on understanding the relationship between user-defined keywords and genres as well as gamer characteristics to understand how to engage players.

About Author

Jason Chiu

Jason is a public health researcher and healthcare quality professional. He is passionate about using data to improve social enterprises. Jason is also an avid music aficionado and an amateur composer. He enjoys a wide range of music,...
View all posts by Jason Chiu >

Related Articles

Leave a Comment

cartier love ring white gold wedding June 22, 2017
Can I whisk or beat the filling since I don’t have a mixer with me? cartier love ring white gold wedding

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI