Neuron Solutions
  • Training
  • Services
  • Projects
  • AI Demos
  • Blog
  • Newsletter
  • Our Team
  • Contact
  • English
    • Magyar
    • English
    • Deutsch
2021.10.20

AI-based recommender systems in practice

AI-based recommender systems in practice
2021.10.20

Our colleague, Gyula gave a presentation on “AI-based recommendation systems in practice” at the Protechtor meetup organised by the Stylers Group and BrainingHub on 30 September 2021.

A recommendation engine is a system that analyses data to provide products, services and information to users. Apart from this, the recommendation is based on a number of factors, such as a user’s history and the behaviour of similar users.

Recommender systems have quickly become a useful tool for service providers and merchants to
help their customers product choice. And in a world of information density and product overload the recommendation engine provides an effective way for companies to provide consumers with personalised information and solutions.

A referral engine can significantly boost revenue and click-through rates (CTR), conversions and other key metrics. It can have a positive impact on user experience, leading to higher customer satisfaction and retention.

Let’s take Netflix as an example. Instead of having to browse through thousands of movie titles, Netflix presents a much narrower selection that is likely to appeal to viewers. This ability saves time and improves the user experience. With this feature, Netflix has achieved a lower unsubscription rate, saving the company around $1 billion a year.

Although recommender systems have been used by companies for nearly 20 years, like Amazon, it has also spread to other industries such as finance and travel in the last few years.

If we want to use a recommender system based on artificial intelligence (AI) in our company’s everyday practice, we don’t necessarily need to research the right AI technologies ourselves, or develop such products. Instead, we could choose existing platforms – frameworks, or even off-the-shelf products. In this presentation we will discuss this “build or buy” dilemma and the decision criteria from the perspective of the recommendation engine discussed earlier, which are one of the main tools used by e-commerce companies (online services, webshops).

During the event, we will address the following questions, among others:

  1. What are the criteria for deciding whether to “buy or build” an AI-based recommender system?
  2. What kind of help can we get from the “outside world” in the scale between “researching” technology solutions or buy “out of the box” products?
  3. Which competences do we need and what tools do we need for different approaches and applications?

The presentation was held in Hungarian, but we can provide trainings, consultation, presentation and deliver projects in English, ofcourse.

AI-based recommender systems in practice: (in Hungarian)

Previous presentation: Types and approaches of AI recommender systems (in Hungarian)

AJÁNLATKÉRÉS
Previous articleWe have given lectures on the practical, business use of Artificial Intelligence in a number of prestigious Hungarian universitiesTöbb egyetemen tartottunk előadástNext article A brief history of Artificial Intelligence

Deep Reading Blog

Recent Posts

Competition issues in the business use of artificial intelligence and other digital technologies2022.06.30
Artificial intelligence: a new workforce in factories2022.06.21
What kind of future do we want for ourselves and what role will artificial intelligence play in it?2022.06.10
  • Magyar
  • English
  • Deutsch

Menu

  • Training
  • Services
  • Projects
  • AI Demos
  • Blog
  • Our Team
  • Contact

NEURON SOLUTIONS KFT

Contact:
1116 Budapest, Építész utca 8-12.
info@neuronsolutions.hu
Billing address:
8220 Balatonalmádi, Szellő utca 7.
VAT number: 26363297-2-19

Adatkezelési Tájékoztató (Privacy Policy)

Neuron Solutions ♥

Neuron Solutions KFT

1224 Budapest

XVI. utca 3 A.

26363297-2-43

info@neuronsolutions.hu

Adatkezelési Tájékoztató (Privacy Policy)