next post: The Power of Instagram to Drive Sales

parcelLab has been named 'Best Unified Customer Experience' by the Vendors in Partnership (VIP) Awards

Learn more
Blog

Recommendation engines - how retailers can use them profitably

parcelLab

Published on: Mar 18, 2019

Zalando takes the place as fashion advisor and About You plays the best friend. Yes, we all know it: “Your style”, “This item suits you…” and “We recommend these products…”. But well, admittedly, they’re almost always right. Because this shirt really goes really well with the jacket you bought in the store the other day. But how do online stores know exactly what we like? The answer is “recommendation engines.” They run in the background. The software is supposed to determine as accurately as possible whether a visitor likes a product or not. To do this, the system filters products according to various criteria.

 

###Performance of the 100 largest German online stores

What are recommendation engines?

[tooltip title=”Recommendation Engines” color=”blue”]Are software systems that aim to make the most accurate prediction possible about a customer’s interest in a product . They aim to suggest to consumers exactly the products they are likely to choose to buy[/tooltip].

 

Recommendation engines have become as much a part of e-commerce as cheese is to pizza. There are different types. On the one hand, there are the systems that work on the basis of content. Product characteristics are compared with the customer’s browsing and buying behavior. If the system finds matches, products are recommended to the buyer. For example, a customer has already ordered a Bob Marley CD and, ideally, given it a good rating. Other items in the reggae genre are now suggested to him.

 

On the other hand, there are systems that work collaboratively. These are a bit more complex because they also involve other users. The system evaluates behavior patterns of different user groups that have given similar ratings to active users. Products that are still unknown to them are then suggested to them. For example: Lisa and Lena are friends. Lisa gives a positive rating to the last hair dryer she ordered. The product is now also suggested to Lena.

 

In content-based systems, the properties of the product are relevant; in collabroative systems, the relationships between users are relevant. However, technologies that combine both are particularly effective. In this way, only truly relevant and personalized recommendations can be issued to customers.

 

These product recommendations can be displayed directly in the online store or sent to customers via customer communication, e.g. in the form of individual shipping messages or personalized newsletters.

 

###Experience shipping messages in action!

What benefits do recommendation engines bring to online retailers?

 

The software systems have some advantages and can have a positive impact on the web store:

  • Increase sales
  • Increase shopping cart value
  • Keep customers loyal to the shop
  • Higher Coversion Rate
  • Increase repurchase rate

 

So what data is most worthwhile for retailers to capture and contextualize? If you target your product suggestions by location, gender, age and income, it’s not very helpful. After all, an old man may be just as likely to buy the latest Nike sneakers as a young man. The solution: the use of recommendation engines. They compare the data of products that are often bought together with the customers’ search and buying behavior.

 

Of course, it is important that the system does not suggest a cell phone to the consumer if he just bought one last week. For new customers, ads such as “top sellers,” “products from the same category,” “similar products” or “products already viewed” are particularly recommended. After all, the merchants still have to get to know the visitors. However, top lists, editorial recommendations or product lists do not count as personalized product recommendations, as these are not specifically made for the individual customer. Amazon, for example, operates customer loyalty with the help of targeted product recommendations.

 

Amazon suggests other similar items to products already searched for. (Source: Amazon)

What are the possibilities?

 

There are several forms of recommendations that merchants can suggest to their customers:

    • Top seller
    • Other customers also bought
    • Our experts recommend
    • You might also like
    • Because you bought XY, you might also like this
    • Matching products
    • Combine products or complete

Depending on the area, other recommendations lend themselves. For technology items, recommended accessories run best. For books, movies and music top seller recommendations are most effective and in the fashion sector is most likely to offer the matching shirt and shoes to the pants. It is particularly important to keep your product recommendations up to date. This means that stores should only offer their customers products that are really available. Otherwise, this could lead to customers being annoyed and possibly abandoning their shopping trip. In addition, online retailers should not overdo it with the number of their recommendations. Websites can quickly become overloaded, which can lead to confusion among consumers.

Fittkau & Maaß Consulting surveyed 120,000 Internet users on their attitude toward personal product recommendations. 15.4 percent have a positive attitude towards these services. 24.3 percent, on the other hand, reject recommendations. 60.2 percent of those surveyed said they were neutral on the subject.

 

Of course, there are places in the web store where recommendations work particularly well. These are primarily start, category, product pages and the check-out. Product suggestions can also be placed in shipping messages. They also make the messages more personal.

 

    • Product pages: Product alternatives based on shopping cart contents and purchase and browsing history increase conversion potential.

 

    • Check-out: Here it is advisable to suggest products that increase both the average order value and the number of items per order. For example, by offering products of the same brand.
    • Search page: Here online stores should offer items that have similarity with the search term or shopping cart.

.

Based on the article, which is already in the shopping cart, the customer is recommended other suitable articles. (Source: Zalando)

 

Conclusion:

 

Personalized product offers should be everywhere in e-commerce in the future, because they are definitely one of the most important e-commerce trends in 2019. Many large stores already use them, but smaller retailers should not do without them either. After all, they bring several advantages. In addition to increasing the value of the shopping cart, you can, among other things, bind customers to the store as well as achieve a higher conversion rate. However, if you decide to use recommendation engines, you should make sure that you use them correctly. Offering outdated or inappropriate products does not go down well with customers. They are particularly effective when placed on home pages, product pages, or in check-out. They are also extremely useful in shipping messages, as they can bring the customer back into the store. But if retailers use the intelligent systems correctly, this can lead to a personalized customer journey and thus contribute to an improved customer experience.

Written by

parcelLab