The online gaming industry in India is exploding. Besides affordable smartphones and data, the pandemic induced-lockdowns have also contributed to this exponential growth. By September 2020, India rose to the number one spot in mobile game downloads worldwide. According to SensorTower’s data, India clocked 7.3 billion gaming installs in the first nine months of 2020, accounting for 17 percent of total installs worldwide.
Indian startups such as Mobile Premier League, Paytm First Games, Winzo and Ewar Games have seen massive growth recently. The mercurial growth of gamers in India has led to surplus data, including first visit or registration, payment methods used by players, playing time, interaction time, withdrawal point, activity peak, and scores.
“Data processing and analysing is an integral part of any industry. It is used to facilitate and control multiple aspects of the business. So if we are to question the role of data analysis in the gaming industry, it will play a pivotal role in understanding and shaping the gaming industry,” said Tarun Gupta, Founder, Ultimate Battle, an online esports platform.
Let’s look at how data analytics can help online gaming and esports businesses scale up.
Data analytics can help gaming companies build interesting scenarios for gamers. For instance, it can tell them the levels that are boring or challenging.
For instance, King Digital Entertainment’s developers were puzzled when many users started abandoning at level 65 of Candy Crush Saga. The game had 725 levels in total, and giving up at level 65 amounted to a huge crisis. The company then approached data analysts to find out what’s wrong and removed the particular gaming element that didn’t let users past level 65. This brought the game back on track.
Around 37% of gamers have cheated at least once, according to cybersecurity firm Irdeto. “Cheating is a perennial problem in video games. Tracking the user behaviour, demographics, time spent helps detect doubtful accounts and prevent and track hacking,” said Lokesh Suji, Director, Esports Federation of India and Vice President of the Asian Esports Federation (AESF).
Many companies have been experimenting with AI systems to resolve the issue. To detect cheaters, Microsoft filed a patent for an AI system in 2019. Carnegie Mellon University published a research paper on cheaters in distributed multiplayer games. Many solutions are being built with the help of unsupervised machine learning algorithms to detect unusual behavioural patterns.
Leading gaming company Valve uses deep learning techniques to spot cheaters in Counter-Strike: Global Offensive (CS:GO). The company created a programme called Overwatch, which used experienced players to watch replays of reported games to detect cheating. This helped the company achieve around 30% conviction rate.
Valve Anti Cheat (VAC) could determine when cheating was happening but could not identify the cheating player. With this data, Valve started using deep learning to build a programme that could learn to identify cheats just like how humans would.
A project of Harvard Business School explains how: “VACnet, as it was later named, used the data from the investigator convictions from Overwatch to train the model, and constantly ran this model across ~3500 processors to scan the 150,000 daily matches played on Valve’s CS:GO servers (McDonald, 2018). Early results showed that conviction rates increased from 15-30% to 80-95% (close to 100% when newly re-trained), but VACnet results were ultimately given to a human to determine guilt and the appropriate punishment.”
Technologies such as motion capture and photogrammetry are used to create visual effects in game development. Photogrammetry uses photographic data and converts them into realistic digital models. Motion capturing creates characters with more human traits. Data analytics can also help esports providers improve the content based on data insights.
Online gaming platforms predominantly have three business models: free-to-play, pay and play and freemium. Big data analytics tools will ensure revenue in all three models.
It will help businesses identify players willing to pay by studying data of their social media activity, playing activity and feedback. Data analysis uncovers key insights ranging from user behaviour, user engagement metrics to business analytics to target players who respond to ads better. “We use data analysts to understand key metrics to design a better user experience, align our marketing efforts and understand business performance metrics to name a few,” said Gupta.
To sum up, as Adam Fletcher of Gyroscope Software explains, “It can seem odd to consider games, often characterized as artistic endeavours, as something you can measure and tune — more like a machine. Data science is no replacement for creativity and design. It is a complement to game design that can support those efforts and fill in gaps that design cannot.”
Subscribe to our NewsletterGet the latest updates and relevant offers by sharing your email.
Shanthi has been a feature writer for over a decade and has worked in several print and digital media companies. She specialises in writing company profiles, interviews and trends. Through her articles for the Analytics India Magazine, she aims to humanise tech in India. She is also a mom and her favourite pastime is playing a game of monopoly or watching Gilmore Girls with her daughter.