Deep learning is a subfield of machine learning and it comprises several approaches to tackling the single most important goal of AI research: allowing computers to model our world well enough to exhibit something like what we humans call intelligence.

On a basic conceptual level, deep learning approaches share a very basic trait. DL algorithms interpret the raw data through multiple processing layers. Each of these layers takes the output of the previous one as its input and creates a more abstract representation of it. As a result, the more data is being fed into the right algorithm, the more general are the rules and features that it’s able to infer in relation to a given scenario and, therefore, the apter it gets at handling new, similar situations.

Google Translate’s science-fiction-like „Word Lens” function is powered by a deep learning algorithm and Deep Mind’s recent Go victory can also be attributed to DL – although the triumphant algorithm AlphaGo isn’t a pure neural net, but a hybrid, melding deep reinforcement learning with one of the foundational techniques of classical AI — tree-search.

Deep learning is an ample approach to tackling computational problems that are too complicated to solve for simple algorithms, such as image classification or natural language processing. However, its current business uses are very limited. It is quite possible that a large portion of the industries that currently leverage machine learning hold further unexploited potential for deep learning and DL-based approaches can trump current best practices in many of them. For instance, one could read several articles in the past couple of months about how DL is going to revolutionize search, with Google’s former head of AI John Giannandrea taking over the company’s search department (and how this could potentially transform the field of SEO, as a whole).

Deep learning fueled recommender systems – the future of personalization

We are pretty sure that deep learning is going to be the next big leapfrog ahead in the field of personalization as well. Personalization constitutes more and more an area of focus for businesses ranging from eCommerce stores to publishers and marketing agencies due to its proven potential to drive sales, increase engagement and improve overall user experience. If data is the fuel of personalization, than recommender systems are its engine. The advances in these algorithms have a profound effect on the online experiences of users across domains and platforms.

Here we look at three specific areas where deep learning can complement and improve existing recommender systems.

Incorporating the content into the recommendation process

Item-to-item recommendations represent a standard task for recommender systems. This means, when an eCommerce store or publisher site recommends another product or piece of content that is similar to the one currently being viewed by the user. One typical approach to tackling this task is based on metadata (another typical data source is user interactions that fuel the Amazon-like “users who bought this item also bought…” logics). However, the poor quality of metadata is a recurring problem in a large percentage of real life situations: values are missing or are not assigned systematically. Even if meta-tags are perfect, such data only represents the actual item much more indirectly and in less detail than a picture of it, for instance. With the help of deep learning, the actual, intrinsic properties of the content (images, video, text) could be incorporated into recommendations. Using DL, item-to-item relations could be based on a much more comprehensive picture of the product and would be less reliant on manual tagging and extensive interactional histories.

A good example of incorporating the content into a recommender system is what Spotify was looking into in 2014, in order to make its song recommendations more diverse and create an improved personalized experience for its users. The music streaming service uses a collaborative filtering method in its recommendation systems. But Sander Dieleman a Ph.D. student and intern at Spotify saw this as their biggest flaw, as such an approach that relies heavily on usage data inevitably underrepresents hidden gems and lesser known songs of upcoming artists – the holy grails of music discovery. Dieleman, therefore, used a deep learning algorithm that he taught on 30-second excerpts from 500,000 songs to analyze the music itself. It turned out, that successive layers of the network learn progressively more complex and invariant features of the songs, as they do for image classification problems. In fact, “on the topmost fully-connected layer of the network, just before the output layer, the learned filters turned out to be very selective for certain subgenres”, such as gospel, Chinese pop or deep-house. In practice, this means, that such a system could effectively make music recommendations based on solely the similarity of songs (an excellent feature for assembling personalized playlists). We do not know for a fact, whether or not Spotify incorporated these findings into its algorithm, but it was nevertheless an intriguing experiment.

Tackling the cold-start problem

The cold-start is the arch-enemy of recommendation systems. It can affect both users and items. For users, the cold-start means when the system has limited or no information on the customer’s behavior and preferences. The item cold-start represents the lack of user interactions with the data upon which item-to-item relations can be drawn (we still have the metadata, though, but that won’t often suffice for truly fine-tuned recommendations). The item cold-start is an obvious domain for the aforementioned content-based approach as it makes the system less reliant on transactional and interactional data.

However, creating meaningful personalized experiences for new users is a much trickier problem that cannot necessarily be solved by simply gathering more information on them. It is quite typical – especially in the case of eCommerce sites or online marketplaces with wide product portfolios – that customers visit a website with completely different goals over time. First they come to buy a microwave, but the next time they’re looking for a mobile phone. In this scenario, the data gathered in their first session is not relevant to the second.

An intriguing approach to tackling the user cold-start problem is session based or item-to-session recommendations. This roughly means that instead of relying on the whole interactional history of customers, the system splits this data into separate sessions. The model capturing the users’ interests then builds on session-specific clickstreams. Through this approach it is quite possible that future recommender systems will not rely so heavily on elaborate customer profiles built over months or even years, rather they’ll be able to make reasonably relevant recommendations after the user’s been clicking away on the site for a while.

This is an area that is yet rather poorly researched, but possibly holds tremendous opportunity for enhancing personalized online experiences. Gravity R&D’s researchers working on the EU funded CrowdRec project recently co-authored a paper that describes a Recurrent Neural Network (RNN) approach to providing session-based recommendations. This is the first research paper that seeks to employ deep learning for session based recommendations and their results show their method significantly outperforms currently used state-of-the-art algorithms for this task.

The Four Moments of Truth

The four moments of truth are the brief time periods when customers make their decisions based on the company’s communication and the available information provided by them. These decisions are heavily influenced by long-term, personal preferences, and brand loyalty, but momentary impressions are also major factors. A deep learning-fueled approach to influencing customers during these Moments of Truth could lead to further, novel insights about the intrinsic human decision process.

We know, for example, that beautiful product pictures can drive sales (whole industries are built around making photos of rental rooms or food). But it would be interesting to assess through a DL-based image analysis approach what exactly are the visual characteristics of a product image that have significant positive effects on sales.

The above list is far from exhaustive. Personalization is no doubt one of the strongest imperatives today in the internet industry as a whole and deep learning almost certainly holds tremendous potential in this area. Therefore, businesses that aim to remain on the cutting edge need to keep an eye out for advancements in the field.

Balázs Hidasi Ph.D., Head of Data Mining at Gravity R&D and CEO, Domonkos Tikk, Ph.D. were expert sources for the article.

Like this article? Subscribe to our weekly newsletter to never miss out!

Follow @DataconomyMedia

I’ve previously written a lot on data mining in the abstract; now, I want to start taking you through some practical applications. Welcome to the fascinating world of the recommendation engine- this post will walk through the concepts, and later posts will teach you how to implement your own.

What we will learn:

I’ll begin our tour by answering four basic questions:

1. What is a recommendation engine?
2. What is the difference between real life recommendation engine and online recommendation engines?
3. Why should we use recommendation engines?
4. What are the different types of recommendation engines?

What is a Recommendation Engine ?

Wiki Definition: Recommendation Engines are a subclass of information filtering system that seek to predict the ‘rating’ or ‘preference’ that user would give to an item.

dataaspirant Definition:  Recommendation Engine is a black box which analysis some set of users and shows the items which a single user may like.

Offline Recommendation Engines

In the external world, we can think of the people around us as recommendation engines.

• Your family and friends as clothes recommendation engines: With the thousands of style options now available to us, we often rely on friends and family to recommend stores, styles and tell us what looks good on us.
• Your Professors and book recommendation engines: When want to research or better understand a concept, our Professors can lead us to the titles which best suit our needs
• Your friends as movie recommendation engines: If you have friends who know your cinematic tastes well, you’re likely to trust their movie recommendations over a random stranger’s picks.

Notice that all of these “offline recommenders” know something about you. They know your style, taste or area of study, and thus can make more informed decisions about what to recommendations would benefit you most. It is this personalisation- based on getting to “know” you- that online recommenders aim to emulate.

Online Recommendation Engines

Facebook: “People You May Know”

Facebook users a recommender system to suggest Facebook users you may know offline. The system is trained on personal data mutual friends, where you went to school, places of work and mutual networks (pages, groups, etc.), to learn who might be in your offline & offline network.

Netflix: “Other Movies You Might Enjoy”

When you fill out your Taste Preferences or rate movies and TV shows, you’re helping Netflix to filter through the thousands of selections to get a better idea of what you might like to watch. Factors that Netflix algorithm uses to make such recommendations include:

• The genre of movies and TV shows available
• Your streaming history, and previous ratings you’ve made.
• The combined ratings of all Netflix members who have similar tastes in titles to you.

LinkedIn: “Jobs You May be Interested In”

The Jobs You May Be Interested In feature shows jobs posted on LinkedIn that match your profile in some way. These recommendations shown based on the titles and descriptions in your previous experience, and the skills other users have “endorsed”.

Amazon: “Customers Who Bought This Item Also Bought…

Amazon’s algorithm crunches data on all of its millions of customer baskets, to figure out which items are frequently bought together. This can lead to huge returns- for example, if you’re buying an electrical item, and see a recommendation for the cables or batteries it requires beneath it, you’re very likely to purchase both the core product and the accessories from Amazon.

Why Should We Use Recommendation Engines?

In the immortal words of Steve Jobs: “A lot of times, people don’t know what they want until you show it to them.” Customers may love your movie, your product, your job opening- but they may not know it exists. The job of the recommender system is to open the customer/user up to a whole new products and possibilities, which they would not think to directly search for themselves.

What Are the Different Types of Recommendation Engines?

Let me introduce you to three very important types of recommender systems:

• Collaborative Filtering
• Content-Based Filtering
• Hybrid Recommendation Systems

Collaborative Filtering

Collaborative filtering methods are based on collecting and analyzing a large amount of information on users’ behaviors, activities or preferences and predicting what users will like based on their similarity to other users. A key advantage of the collaborative filtering approach is that it does not rely on machine analyzable content and therefore it is capable of accurately recommending complex items such as movies without requiring an “understanding” of the item itself. Many algorithms have been used in measuring user similarity or item similarity in recommender systems. For example, the k-nearest neighbor (k-NN) approach and the Pearson Correlation.

Content Based Filtering

Content-based filtering methods are based on a description of the item and a profile of the user’s preference. In a content-based recommendation system, keywords are used to describe the items; beside, a user profile is built to indicate the type of item this user likes. In other words, these algorithms try to recommend items that are similar to those that a user liked in the past (or is examining in the present). In particular, various candidate items are compared with items previously rated by the user and the best-matching items are recommended. This approach has its roots in information retrieval and information filtering research.

Hybrid Recommendation Systems

Recent research has demonstrated that a hybrid approach, combining collaborative filtering and content-based filtering could be more effective in some cases. Hybrid approaches can be implemented in several ways, by making content-based and collaborative-based predictions separately and then combining them, by adding content-based capabilities to a collaborative-based approach (and vice versa), or by unifying the approaches into one model. Several studies empirically compare the performance of the hybrid with the pure collaborative and content-based methods and demonstrate that the hybrid methods can provide more accurate recommendations than pure approaches. These methods can also be used to overcome some of the common problems in recommendation systems such as cold start and the sparsity problem.

Netflix is a good example of a hybrid system. They make recommendations by comparing the watching and searching habits of similar users (i.e. collaborative filtering) as well as by offering movies that share characteristics with films that a user has rated highly (content-based filtering).

I hope you liked today’s post. In the next installment, we’re going to learn about these three recommendation systems in the bigger picture, and learn how to implement them. Any questions? Leave a comment below.

Featured Image Credit: clasesdeperiodismo / Foter / CC BY-SA
Body Image Credits: Yuriy Trubitsyn / dataaspirant
Original source can be found here.

Following on from their acquisition of VisualGraph last year, Pinterest are back on the machine learning acquisition hype with their latest purchase, Kosei. Kosei is machine learning startup that is led by data scientists & recommendation engine specialists.

“Over the past year, Kosei has been building a unique technology stack that drives commerce by making highly personalized and powerful product recommendations, as well as creating a system that contains more than 400 million relationships between products,” explains Michael Lopp, the head of engineering at Pinterest.

Kosei’s proprietary recommendation engine assists with greater engagement and commerce by making highly personalized and powerful product recommendations to consumers by leveraging a unique product graph that understands products and how they relate to each other.

Pinterest listed out its strategy with the newly acquired ML tool as follows:

• The Black Ops team uses classification to detect spam content and users

• The Discovery team (which includes search and recommendations) provides recommendations, related content, and predicts the likelihood that a person will Pin content

• Our Visual Discovery team is working with cutting-edge deep learning algorithms to do object recognition and related object recommendations

• The Monetization team does ad performance and relevance prediction

• The Growth team has begun to move into the realm of using intelligence models to determine which emails to send and prevent churn

• The Data team is building out a distributed system for machine learning using Spark, so the learning can be efficient and potentially real-time

With a data set of over 30 billion Pins and growing still Pinterest intends to upgrade the existing graph to help brands optimize the customer interaction to ‘reach people at the right moments, and improve content for Pinners.’

Read more here.

Follow @DataconomyMedia

(Image credit: MKHMarketing, via Flickr)