A Beginner’s Guide to Deep Reinforcement Learning
The game of Go has simple rules but complex play. Each turn, a player has something in the vicinity of 2 x 10170 board positions to consider. Experienced players learn what is likely to work by trial and error over years of play in a process known as reinforcement learning.
So what do you get when you give artificial intelligence (AI) the data from thousands of games between professional Go players? AI that beats the top-ranked human Go player – AlphaGo. That is deep learning in action.
But what if instead you teach AI the rules of Go and let it play millions of games between itself? Deep reinforcement learning enables AI to teach itself by creating its own data (the millions of games) and analyzing the moves to arrive at the best one. Like a learning human, AI adjusts its responses according to failure or success to improve the outcome. It just does it at a scale and speed well beyond human capability.
Deep reinforcement learning needs to work inside a structure. This takes into account the context of the environment – whether that is the rules of Go, or the market in the case of your campaign – before you set a goal. An AI with deep reinforcement learning will then be able to help you with your strategy and actions based on the lessons learnt not only from previous campaigns, but also from the scenarios it has played out in its own internal iterations to give you an understanding of what is likely to happen.
It will also continue to learn as you roll your campaigns out, figuring out not just what works and what doesn’t but analyzing factors such as profitability, so you can optimize future campaigns by lowering your cost per lead, for example, or by targeting users who are likely to spend more.
Consider a campaign in which you want to maximize the number of app installations. You have a budget, so the aim is to obtain the highest number of installations for the amount you have (goal). You need to figure out where to allocate your budget and what to set as the bid price (actions). Using the deep reinforcement learning technique, AI will suggest a strategy based on its understanding of budgets and prices to find the best platforms and timing. It will suggest actions for you so you can leverage the most advantageous opportunities. And if the environment changes, it will learn what works and what doesn’t much quicker than a human marketer.
Deep reinforcement learning is ideal for complex environments where there are several alternative paths, such as marketing where you are dealing with human behavior. Its most valuable advantage is that it learns from mistakes in order to optimize quickly.
WE ARE HERE TO HELP
YOU MIGHT ALSO LIKE
By Junde Yu, Chief Business Officer, Appier Josh Shozen, Senior Vice President of Enterprise Solution Sales for Japan and South Korea, Appier I’m excited to welcome Satoshi (Josh) Shozen to our team as Senior Vice President of Enterprise Solution Sales for Japan and South Korea. Based in Tokyo, Josh brings over 15 years’ experience in enterprise software sales management and digital marketing in Japan and the region where he has worked with global technology companies including Adobe, Proscape Technologies, and Microsoft. Before joining Appier, Josh was the country manager for SundaySky Japan, the creator of SmartVideo platform, and helped develop the strategic partner ecosystem for selling into major FSI and Automotive clients. In his new role, Josh will lead our teams in both countries to strengthen the business of Aixon, an AI-powered Data Intelligence Platform that Appier launched last July. More than 10 clients, including Japanese real estate portal LIFULL, have already successfully deployed Aixon and transformed their digital marketing campaigns. While we continuously upgrade technology for Aixon’s functionality to help our customers’ business success, such as the recent integration with LINE Business Connect, we also see the strong potential of our business in both the marketing and data intelligence platforms.
It’s a norm for marketers these days to drive meaningful engagement with returning customers through personalized marketing campaigns and content. However, with marketing automation tools powered by artificial intelligence (AI), you can now personalize your website content for first-time visitors to turn more traffic into conversions. In today’s noisy digital space, brands place high premium on personalizing their content and services to their audiences. Tailoring the content on an app or a website to match visitors’ interest can be a powerful way to convert them into leads or even buyers. According to the 2018 Personalization Pulse Check from Accenture Interactive, 91 percent of consumers are more likely to purchase from brands that provide relevant offers and recommendations. How Far Can Traditional Methods Go? Marketers have so far approached personalization by researching the existing customers and refining target personas to create more tailored content over time. As you get more data on the type of visitors who return to your site or app, you get a better understanding of the creative that should be produced for these visitors. While this helps in delivering personalized experiences for returning customers, a major portion of visitors convert on their first visits. According to a
Although app downloads continue to rise, app abandonment and fraudulent use – where bots steal from app marketers via methods such as false referral attribution – threaten to undermine brands’ efforts at achieving return on investment. Marketers have therefore turned away from app installations as a measure of return and now look at in-app spending and the lifetime value (LTV) of a customer. By 2022, global mobile app downloads will hit 258 billion and in-app spending will reach US$157 billion. Competition is likely to heighten as apps vie for attention, so it is important for you to engage users as soon as they install and open the app. Completing an in-app event, from agreeing to receive push notifications to starting a subscription, increases the chances of retention – a key marker for customer LTV. Unfortunately, user engagement and retention is an area where 55 percent of marketers consider their biggest challenge. Complicating matters is the prevalence of fraudulent installs and false in-app actions, which rose significantly in 2018 at a cost of about US$19 billion for app marketers. Artificial intelligence (AI) can identify the traits and behavior of high-value app users and help you acquire them, as well as support