It is easy to get confused about recommendation systems as they are also called recommender systems or recommendation engines. All of these perform the same actions, they are systems that predict what your customers would want by analyzing their behavior which contains information on past preferences.
This article will explain recommendation systems, including how it works, application areas, examples from companies that use recommendation systems, benefits & potential vendors.
Almost any business can benefit from a recommendation system. There are two important aspects that determine how much a business benefits from a recommendation system:
- Breadth of data: A business serving only a handful of customers that behave in different ways will not receive much benefit from an automated recommendation system. Humans are still much better than machines in the area of learning from a few examples. In such cases, your employees will use their logic, qualitative and quantitative understanding of customers to make accurate recommendations.
- Depth of data: Having a single data point on each customer is also not helpful to recommendation systems. Deep data about customers online activities and if possible offline purchases can guide accurate recommendations
With this framework, we can identify industries that stand to gain from recommendation systems:
Industry where recommendation systems were first widely used. With millions of customers and data on their online behavior, e-commerce companies are best suited to generate accurate recommendations
Target scared shoppers back in 2000s when Target systems were able to predict pregnancies even before mothers realized their own pregnancies. Shopping data is the most valuable data as it is the most direct data point on a customer’s intent. Retailers with troves of shopping data are at the forefront of companies making accurate recommendations
Similar to e-commerce, media businesses are one of the first to jump into recommendations. It is difficult to see a news site without a recommendation system.
A mass market product that is consumed digitally by millions. Banking for masses and SMEs are prime for recommendations. Knowing a customer’s detailed financial situation, along with their past preferences, coupled by data of thousands of similar users is quite powerful.
Shares similar dynamics with banking. Telcos have access to millions of customers whose every interaction is recorded. Their product range is also rather limited compared to other industries, making recommendations in telecom an easier problem.
Similar dynamics with telecom but utilities have an even narrower range of products, making recommendations rather simple.
How does it work?
Recommendation systems collect customer data and auto analyze this data to generate customized recommendations for your customers. These systems rely on both implicit data such as browsing history and purchases and explicit data such as ratings provided by the user.
Content based filtering and collaborative filtering are two approaches commonly used to generate recommendations. For more, please read the approaches section of our list of recommendation system vendors.
Benefits of recommendation systems
There are very few ways to achieve increased sales without increased marketing effort. Once you setup an automated recommendation system, you get recurring additional sales without any effort.
Increased user satisfaction
Shortest path to a sale is great both for you and your customer reducing their effort. Recommendation systems allow you to reduce your customers’ path to a sale by recommending them an appropriate option sometimes even before they search for it.
Increased loyalty and share of mind
By getting customers to spend more on your website, you can increase their familiarity with your brand and user interface, increasing their probability to make future purchases from you.
Recommendation system powered emails are one of the best ways to re-engage customers. Discounts or coupons are other effective yet costly ways of re-engaging customers and they can be coupled with recommendations to increase customer’s probability of conversion.
Examples from companies that use a recommendation engine
Amazon.com uses item-to-item collaborative filtering recommendations in most pages of their website and e-mail campaigns. According to McKinsey, %35 of Amazon purchases are thanks to recommendations systems. Some example where Amazon uses recommendation systems are
Netflix is another data-driven company that leverages recommendation systems to boost customer satisfaction. Same Mckinsey study we mentioned above highlights that 75% of Netflix viewing is driven by recommendations. In fact, Netflix is so obsessed with providing best results for users that they held data science competitions called Netflix Prize where one with the most accurate movie recommendation algorithm wins a prize worth $1,000,000.
Every week, Spotify generates a new customized playlist for each subscriber called “Discover Weekly” which is a personalized list of 30 songs based on users’ unique music taste. Their acquisition of Echo Nest, a music intelligence and data-analytics startup, enable them to create a music recommendation engine that uses three different types of recommendation model:
- Collaborative filtering: Filtering songs by comparing users’ historical listening data with other users’ listening history.
- Natural language processing: Scraping the internet for information about specific artists and songs. Each artist or song is then assigned a dynamic list of top terms that changes daily and is weighted by relevance. The engine then determines whether two pieces of music or artists are similar.
- Audio file analysis: The algorithm each individual audio file’s characteristics, including tempo, loudness, key and time signature and makes recommendations accordingly.
Just like any other social media channel, linkedin also use “You may also know” or “You may also like” type of recommendations.
Setting up a recommendation system
Recommendation systems in the market today use a logic like: customers with similar purchase and browsing histories will purchase similar products in the future. To make such a system work, you either need a large number of historical transactions or detailed data on your user’s behavior on other websites.
There are plenty of vendors as you can see on our vendor list for recommendation systems. You can use historic or even better, live data to test effectiveness of their systems. Including code snippet of the vendor may be enough to get started.
More data and better algorithms improve recommendations. You need to both make use of all relevant data in your company and make sure you expand your customer data with 3rd party data providers like the ones we listed. If a regular customer of yours has been looking for red sneakers on other websites, why shouldn’t you show them a great pair when they visit your website?
Choosing a partner
Recommendation systems are one of the earliest and most mature AI use cases. There are 50+ vendors providing services. Some of the vendors are listed below. Visit our guide on recommendations systems to see all the vendors and learn more about recommendation engines.
Salesforce.com founder Marc Benioff has done his part of revolutionizing the software industry “world’s first comprehensive AI for CRM.” Einstein recommendations can be easily integrated to your offering if you are already a Salesforce customers.
It isn’t often that we hear that an 18-month-old startup raised $56 million by Goldman Sachs. Antuit is quite well funded.
The founder and CEO of Clarifai Matt Zeiler is an AI expert with a Ph.D. in machine learning from NYU. Clarifai has proven its image recognition capabilities since winning the top five places in image classification at the ImageNet 2013 competition. Leveraging clarifai system, e-commerce companies can offer similar looking merchandise as recommendations.
A slightly better recommendation engine could boost a companies sales by a few percentage points which could make a dramatic change in the profitability of a company with low profit margins. Therefore, it makes sense to invest in building better recommendation engines even if the company is already using one. One possible approach is to use the wisdom of the crowd to build such systems. Companies can use encrypted historical data, launch data science competitions and get models building highly effective recommendations. We can help you identify partners in building custom recommendation engines:
If you want to learn more about custom AI solutions, feel free to read our whitepaper on the topic:
AI is not only applied to recommendation personalization. You can check out AI applications in marketing, sales, customer service, IT, data or analytics. And if you have a business problem that is not addressed here:
How can we do better?
Your feedback is valuable. We will do our best to improve our work based on it.