top of page
  • Philipp Derksen

6 problems in eCommerce that should no longer exist thanks to AI

Updated: Dec 2, 2022

E-commerce is virtually made to use artificial intelligence. Philipp Derksen of Vviinn on smart algorithms and problems that AI could easily solve.

In a nutshell, artificial intelligence is about one thing: the ability to predict things and developments. With the help of machine learning, smart algorithms learn to recognize patterns in data and make predictions accordingly. E-commerce is made to use this technology. It is a fully digital business model in which large volumes of data are generated. And predictions have to be made constantly. Which customers are interested in which products? What is the best way to address them? How will sales and inventories develop? Artificial intelligence can answer many of these questions - and has thus solved or even eliminated some long-standing problems of online retailing, which, to be frank, should no longer exist today. Here are the six most important ones.

Non-specific and irrelevant customer approaches

AI helps to make shopping experiences more individual and personal. The myth of personalization may have lost some its appeal in digital marketing by now. In online retail, however, the smart use of artificial intelligence has proven to be very promising. AI analyzes user data and recognizes patterns and regularities. With the help of CRM data, newsletters can be customized to be more interesting and personal. Based on data and previous buying behavior, the user experience as a whole becomes more individual and specific. To give an example: a customer who has shown a predominant interest in office furniture in the past will be shown corresponding offers in the future with the help of AI.

The elaborate art of product descriptions

A major challenge for all online stores is text production. Descriptions have to be written for thousands of products. And make no mistake: good texts are a sales factor as they should not only present the products accurately, but also encourage people to buy them. AI helps to shorten and ease this time-consuming and labor-intensive work. Numerous software solutions are offered on the market that retailers can use to improve their product texts and make them more successful. With AI language technology, product descriptions can now be created automatically and in a consistent style. At the push of a button, the software generates a variety of product descriptions, adapted to seasonal topics such as discounts and, if desired, in different languages.

Poor user experience due to lack of relevance

Ultimately, the design of many online stores is based on text navigation. As a legacy from the web 1.0 era, it prevents the mobile shopping experience from being what it should be: a fun, intuitive journey. A key technology to change that is Visual Search, which is becoming more and more prevalent. Google Lens and Bing image search have made searching with photos a learned cultural technique with an added value for online stores. Visual Search helps you find things that you can't exactly name or describe. Is the furniture you're looking for a sideboard or rather a chest of drawers? The simple answer of Visual Search is to upload a photo in the search field and to immediately receive offers for the very same or a similar product.

Call center queues and unqualified support requests

Few things can spoil a positive shopping experience as much as having to wait for what feels like ages in a call center queue. Text assistants and chatbots provide a remedy, though, as they are available 24/7, taking a significant load off the call center. Such technology is not new, but thanks to the artificial intelligence it is becoming increasingly smarter. Chatbots can now interact with customers in ways similar to real salesperson and manage to answer up to 80 percent of simple and recurring requests. In doing so, they give human call center agents more time and leeway to deal with more complicated inquiries.

Bottlenecks and too much remaining stock

It’s a particularly annoying situation for retailers: a customer has found the desired product in the store and wants to order it, but it is currently out of stock. Up to this (crucial) point, the customer journey went as desired - now the purchase fails due to logistics. The customer will buy somewhere else and probably never come back. Artificial intelligence helps to better manage inventories and anticipate such bottlenecks at an early stage. Machine learning systems let us know early and in real time when demand for certain products will increase. Here, visual search technology offers some untapped potential. It can be used to automatically categorize products and generate attributes according to a consistent scheme. Accurate predictions of future sales volumes become possible based on a new product’s visual similarity to products with historical sales data.

Payment defaults and payment-related cancellations of purchases

A problem for years in e-commerce that has been successfully combated with the help of AI technology. Anyone involved in online payment is regularly confronted with payment defaults. Some customers simply forget to pay their bill, others are unable to pay - some defaults are the result of criminal energy and credit card fraud. AI is helping both e-commerce and payment service providers better manage these challenges. Smart algorithms recognize patterns that indicate fraud or an inability to pay. Thanks to their learning ability, systems can react flexibly, only blocking transactions that are actually fraudulent. For some time now, major players in e-commerce have used artificial intelligence in a wide variety of forms with much success. Still, this technology has not yet gained widespread acceptance in the industry. Given the fact that even medium-sized, small and specialized stores can benefit from AI with little effort, this is rather surprising. Self-learning algorithms have proven their worth many times over, especially when it comes to the greatest challenge of online retail - the never-ending improvement of user experience. In the end, it's not about technology. It's about creating a positive shopping experience.

About the author: Philipp Derksen is the founder and product owner of Vviinn - an AI-based software solution for visual product search and product recommendations in online shops. The Berlin entrepreneur and engineer has been working in the online industry for over 20 years and in e-commerce for 15 years. His company Mediaopt has been developing software solutions for the e-commerce industry since 2009 and advises companies on their digital sales strategy.

The origin article was published in Werben & Verkaufen (abbreviated to W&V), a trade magazine for the communications and media industry.


bottom of page