3 Reasons Your Company Needs A Recommendation Engine


We are willing victims to the power of recommendation engines, but harnessing one is not an instant download, yet. Here’s why you need one and how to get it.

Without fail, we can’t talk about recommendation engines without acknowledging the brilliance of Youtube and Netflix– their recommendation engines are a renowned technique to keep customers engaged and subscribing month after month. Now mimics everywhere make the hot claim to associative-fame saying, “like Youtube for {insert industry x}.” They started a revolution, but despite the number of years we’ve all been willing victims to their power, the advanced algorithms are not quite an instant download that you can apply to your own company yet.

In this article, we’ll lay out some interesting ways recommendation engines are being used and how you can get your hands around the reigns of your own. Beyond the widely used applications of recommendation engines to convert more sales and improve customer retention, we’ll show you even more ways you can make money. We’ve deduced the benefits and recommend these 3 reasons why your company needs a recommendation engine now.

1. Highly personalized product recommendations

This is the best-known use case for product recommendations. If you have a large number of products or an e-commerce website, make product recommendations your focus. You’ve seen it on Amazon, Netflix, and other consumer websites. In B2B sales, a product recommendation engine is also useful because it can provide upsell suggestions for your sales representatives.

2. Optimized Customer Loyalty Programs

According to the 80/20 principle, a minority of your customers will account for a large amount of your sales. These highly engaged customers deserve special treatment, so they keep buying and referring more customers to you. Use a recommendation engine to identify your highly engaged customers and give them special offers and rewards. For instance, instead of offering every customer a 10% off coupon for Black Friday, offer something personalized (e.g., “get a 2 for one offer on all the products you’ve purchased in the past six months”) to your loyal customers.

3. Tailored advertising

In digital advertising, you have the chance to test many different advertising messages. When you have hundreds or thousands of online ads running, identifying winners becomes difficult. That’s where a recommendation engine can help you. For example, Google Ads includes a recommendation engine that provides suggestions on ways to get more traffic by increasing bids.

Case Studies:

On-screen Retail Product Detection and Recommendations

AiBUY is an onscreen shopping tool that utilizes computer vision to recognize products within images and videos, in real-time. Currently, they are focusing on the onscreen detection of fashion items and embedding the shopping tool to enable immediate purchase without being redirected or leaving the screen. A user would simply be watching their favorite content when the AiBUY shopping tool would prompt the viewer with purchasing the items in view.

During an interview with AiBUY’s CTO, Ryan C. Scott, he explained how it works, saying, “Firstly the focus was on detecting a person and their gender. Secondarily adding various other classes e.g. if a woman, then dresses, blouses, etc,” similar to nested categories on most fashion sites. The detected images are then searched within a given retailer’s integrated catalog and the most relevant products are recommended. Scott explains, “By integrating directly with the retailer’s eCommerce platform, we import and synchronize the product information and ensure data like inventory levels and product variance selections are maintained.” Noting one of the latest improvements was “the use of the Annoy library(by Spotify) to improve the performance functionality in searches of nearest neighbors for product classification.” Nonetheless, as Scott humbly remarks “we are always reviewing our codebase to find potential bottlenecks so we can continuously evolve and adapt to the ever-changing outer world.”

Scott continues with more exclusive behind the scenes on how they built it, saying, “The AiBUY system is based on a TensorFlow framework and uses Python as the main language. The training dataset holds about 400,000 images with excellent categorical markup, aggregated and prepared with the help of scripts, supplemented by 1,200,000 images of mixed or poor categorical markup quality from external Affiliate Network companies.” From this rigorous model training, their system is able to recognize clothing worn in your favorite shows, but instead of recommending the next show, it’ll show you where you can buy that swimsuit or other recommended options instantly.