AI News, Scopely and the Uses of AI and Analytics in Gaming

Scopely and the Uses of AI and Analytics in Gaming

Episode Summary: One of the most clear insights from our recent consensus on machine learning in marketing was that companies who have more digital touch points along the path to conversion—and more conversion in general—have an advantage when applying AI and ML technologies.

Ask yourself: Has the business problem that you’re working on historically been solved with good results through simpler regressions, heuristics, or other models? If you’re lacking the necessary machine learning infrastructure (a robust data platform, for example) and not working on areas where machine learning almost always has the advantage (say advanced analytics), then the cheaper and quicker tool may be the better option for making early progress.

AB: We want to keep them highly engaged, we don’t judge them by recurring payments as much as we do cumulative lifetime spend, so the whales are those people who have spent the most in your game, and it depends on the game…in some cases you may be buying acceleration to make something happen…we also run a lot of live events, and the live events—these are things like tournaments or alliance wars…and these social competitive events help to drive a lot of monetization, and it’s very reusable…instead of selling physical goods, we’re selling virtual goods, and just like any eCommerce platform, it’s up to us to keep that merchandise fresh, to create sales and opportunities to spend, to create want and desire, to create vanity and social competition…

AB: Taking a quick step back, the first thing we had to do—and I think this is important for any company—is we had to build a data platform…we had made the mistake before of trying to apply ML to a poorly formulated data set, and there’s an old adage in data of “garbage in garbage out”, and really until you get rid of the all the garbage coming in your data platform, it’s hard to build any kind of modeling…we’ve taken very significant strides, and I’d say now we have a quite robust and highly competitive analytics platform, compared to what’s in the commercial marketplace…and once we were able to do hindsight analysis in an accurate way, we started considering what is the predictive stuff we can do…

This is important because you need to calibrate your bids, and rather than make up a bid, you want to have some confidence that you are not overpaying and you want to bid as high as possible in a growth phase without bidding above your LTV…it’s really critical at first to get these games at scale, because if we don’t, you’re going to have a hard time creating enough social critical mass to make the game interesting, to create enough social competition, to create enough of a user base.

AB: That is a more accurate description, and the other point I would make is that the other reason why we can’t wait four or five months…is the game will have evolved so much in that five months that essentially it’s a different game…this goes back to live content and frequent updates, and we try to have one release a month with a big new feature…one of the things we look for, from a data perspective, is are the new cohorts monetizing at a higher level than the old cohorts?

Uber’s Head of Machine Learning, Danny Lange, speaks at the Kaizen Data Conference

Watch Uber's Head of Machine Learning, Danny Lange, discuss past, present and future advancements in machine learning. This compelling talk covers AI's ...

Stanford Seminar: HPC Opportunities in Deep Learning

EE380: Computer Systems Colloquium HPC Opportunities in Deep Learning Speaker: Greg Diamos, Baidu Just this year, deep learning has fueled significant ...

Implementing and Training Predictive Customer Lifetime Value Models in Python

Implementing and Training Predictive Customer Lifetime Value Models in Python by Jean-Rene Gauthier, Ben Van Dyke Customer lifetime value models (CLVs) ...

How to make a Motherboard - A GIGABYTE Factory Tour Video

The motherboard in this video are part of the Ultra Durable series. Our current Z170 recommended motherboard from this series is the Z170 UD5 ...

Build Your Own Event Analytics Pipeline Using BigQuery, Dataflow, and K8s (Cloud Next '18)

Traditionally, a lot of companies rely on off-the-shelf data analytics platforms for product analytics to understand each user's journey. However, if your product ...

A/B Testing

This video is part of the Udacity course "Engagement & Monetization | Mobile Games". Watch the full course at

All of our data is GONE!

We experienced a MASSIVE RAID failure on Whonnock server and lost a crapload of data. Can we get it back? Rackspace has your Dedicated Environments ...

How to fix a dead arcade game #1 - Troubleshooting a Craigslist purchase - Data East Commando

Like the vids? Sponsor John's Arcade!: Enjoy the vids? Consider supporting me! Thank you, John

Reco4: A Recommendation Engine Exploiting Machine Learning on Big Data

This session takes a close look at the Reco4 recommender, a Java graph-based recommendation engine. Today the most advanced types of these ...

DEFCON 19: Hacking MMORPGs for Fun and Mostly Profit ( w speaker)

Speaker: Josh Phillips Senior Malware Researcher Online games, such as MMORPG's, are the most complex multi-user applications ever created. The security ...