Update Recommender System: Never miss updates and exciting articles on your topics again

Our unique recommender system helps learners stay up-to-date on their topics and continue to develop. We compare learner data with new articles, studies, and courses found on deposited websites, internal company sources, or optionally on the Internet in general. Find out in this article exactly what we offer our customers and how it works.

What are Recommender Systems?

A recommendation system, also called a recommender system, is a software solution that makes personalized suggestions or recommendations to users for products, services, or content. It is based on the user’s preferences, behavior and interactions. Such systems are often used in online stores, streaming platforms, social networks, but also on modern learning platforms like chunkx. On learning platforms, they are only usually limited to recommending new courses to learners from the respective platform or from a limited number of partners. We think this can be done better!

Recommender Systems in chunkx

In chunkx, we not only process which courses a learner is taking, but we can directly analyze the content of the many individual learning units. This allows us to make comparisons in terms of content. For example, if you learn a lot about diverse leadership, we can use the content of your learning units and your learning data to match them with skills and generate appropriate recommendations:

1) Matching courses in chunkx
Okay, that’s not a surprise yet, but it’s a very important feature for our customers who use our micro-learning platform.

2) Suitable courses outside of chunkx
Now we are getting closer to innovation. Using AI and well-placed data extraction, we can find suitable courses for you to continue learning. Skills, development goals and other parameters can also be taken into account.

3) Articles, studies and updates
chunkx already supports you intensively in the transfer of learning. But with our recommender system, we also make it easy for you to benefit from new articles, studies, and general updates on your topics. Let’s stay with the example of Diverse Leadership: If you have a great course with a subsequent learning subscription in chunkx, you don’t want to stop at this level of content, but rather continue to develop. As long as you keep the subscription to the channel, we will automatically compare your learning data and skills with newly found items and let you know as soon as we find something suitable for you! In this way, we support you not only in the transfer of learning, but also in continuous learning.

Recommendation sources

Quality is a core requirement for our automatically generated recommendations. The first step towards this is to control the sources from which new recommendations may be generated in principle. There are different levels here:

  1. Selected sources
    Together with our customers, we determine which sources they want us to crawl on a regular basis. This ensures that only sources requested by the customer are considered for new recommendations. Crawling means that a robot looks at the website again and again and analyzes what new has been published. This content is vectorized to make it easier to compare with learning data.
  2. In-house sources
    Of course, customers have even more control over their internal data. And these can also be used for recommendations: Similar to the approach above, we vector internal data, e.g., that of a product database or knowledge platform, and respond to identified knowledge gaps in learners with the perfect recommendations on internal articles.
  3. The free internet
    Especially for topics that are highly topical, such as Generative AI, and where things can change on a daily basis, we recommend that customers refrain from restricting sources. Without this restriction, we can find even more suitable recommendations for courses, articles and updates.

Validation of recommendations

Especially with innovative automation, it is important to set up the validation of the results properly. Depending on the use case, an initial validation is already ensured via the restriction and selection of sources. Since our recommender system is primarily based on content proximity between learning units and new courses or articles, there is basically a very good chance of a good fit. All results that are good enough from this point of view end up on a shortlist.

We then have the shortlist analyzed with GPT-4 and compared again with the baseline situation, i.e. the learner data. We only use services via Microsoft Azure here, so we can ensure that none of OpenAI’s data may be used outside of our specific purpose and that all data is processed in Europe (specifically, in France). After processing, a few top results remain.

The top results are humanly checked again before publication, so that really nothing can go wrong. This is true for our asynchronous recommendations, but not for adhoc recommendations, for example, when a learner wants a new course recommendation right now.

Linking with next learning unit

In the image above you can see an example of a recommendation sent by email. What you see below the recommendation: every communication event is used by chunkx to send learners the next learning unit. In this way, we support continuous learning and enable learning directly in the flow-of-work in the channels that people already use anyway (currently we support email and MS Teams).

When do you start with chunkx?

With chunkx, we’ve created the solution to turn your one-off learning activities into continuous learning experiences, including through our recommender systems. Talk to us about your learning culture and the changes in your organization and how chunkx can best support you.

Corporate Learning redefined: With ChatGPT and other smart technologies for sustainable and individual employee development

ChatGPT and other smart tools not only bring opportunities for more efficient content creation, but also open up whole new opportunities for sustainable employee development and professional development.

Digital Learning: The challenge of the growing flood of content

In a rapidly changing world of work, it is of great importance for companies to qualify their employees for the requirements of the future. In doing so, they face two major challenges:

  1. There is no endless stream of new employees to recruit who already bring new skills and experience to the company. On the contrary, the choice is very limited and companies are struggling to find the best offers and concepts to attract talent and appear attractive as an employer brand.
    #employerbranding #skilledlaborshortage
  2. “The world is changing faster and faster,” is a statement that may evoke a weary yawn from most people. Fair enough! Nevertheless, in light of the first challenge, continuing education is a constant and ongoing need for companies, particularly when it comes to preparing employees for unknown future challenges. Especially in terms of empowering employees to best deal with new challenges that we don’t know about yet.

Accelerated by the Covid crisis, digital training has become a top priority for companies. The proliferation of new platforms, customized trainings, and eLearning offerings has resulted in an ever-growing flood of content.

Content vs. impact

However, it is unclear how effective these measures are. How much knowledge is actually retained? How much does a company benefit from courses that end abruptly and rely on learners either internalizing everything in detail immediately or looking at slides on their own later?

As the amount of learning content increases, attention to the individual topic inevitably decreases, and in the rush of daily work, content tends to fly by rather than take root. But how to solve this? How can individual follow-ups be generated on the topics employees are working on? How can we technologically create learning companions through which learning processes are thought of continuously instead of once and which can also react to changes on an ongoing basis? Who is going to be able to handle all this work?
I’m sure you already have an idea of the direction the answer will take. 😊

New possibilities with ChatGPT and other smart technologies

Thanks to extreme scalability, ChatGPT and other smart technologies offer a new form of sustainable and individual employee development. At chunkx, we use technology like this in many places to provide companies with a subscription option to any learning activity in their organization. In doing so, we take on the task of ensuring the impact and retention of the learning for each individual employee. There is more on our main page.

But how do we use ChatGPT and other smart technologies now? Here are a few examples:

1. Efficient and scaled content creation

Just a few months ago, it would have seemed inconceivable for 99% of Learning & Development leaders to create personalized microlearning units for potentially all learning activities in their organization and to individually select follow-ups based on knowledge levels. But now that most of them have had their first touches with OpenAI’s ChatGPT, it’s starting to become more tangible how high the quality of automatically created content has become.

What is often still a difficulty is a lack of context and a not inconsiderable proportion of false statements that nevertheless sound right. At chunkx, we solve both by creating the necessary context with content that exists inside or outside the company in the form of PDFs, WBTs, PowerPoints, or learning videos. Herewith ChatGPT and other language models have the necessary orientation to create suitable microlearning units.

2. Smart content selection

Imagine receiving follow-ups to every learning activity you participated in to enable learning transfer. You’d drown in emails and learning content and end up ignoring it because it’s just too much and overwhelming.
At chunkx, we have developed our own algorithms to choose the right one for you from a number of thousands of microlearning units or, if necessary, to repeat one you have already worked on. Always with the aim of promoting learning transfer and ensuring sustainable learning success. Only through such a technology, which can guarantee the necessary reduction for the individual user for a wide variety of topics, can the acceptance and thus the overall success of the learning measures be ensured.

Language models and Natural Language Processing help us with smart or adaptively called content selection, e.g. via content tagging. We have written more about this here.

3. Personalization of the learning content

We have already created microlearning units to our existing trainings and courses in step 1. In step 2, we make sure that the content is selected appropriately per user. Now we’re going one step further and enabling language models like ChatGPT to be used to further personalize content as well. Thus, content can be made easier or harder as needed, alternative variants of the content can be created for different roles, or examples can be formulated more appropriately for the profile in question. All these measures, still consumed a lot of working time without AI solutions and were therefore suitable for high-priced learning measures. Our Machine Learning team is already experimenting with this and looks forward to discussing your company’s content personalization needs as well!

4. Recommendations for further learning

Continuous learning for us includes using technology to also find new content for the learner that fits his or her courses and training. If someone has taken courses on cyber security, or “subscribed” as we call it, then a newly published article on current phishing methods would be a fitting recommendation, enabling and encouraging continued learning.
Perhaps not only external open source content, but also courses from linked platforms, such as LinkedIn Learning should be considered when generating recommendations.
Or even the internal, non-public database with all knowledge articles should be related to the processed learning content and the right recommendations should be generated.
All this is part of our concept of how continuous learning can work with the help of ChatGPT and modern technologies.

Use ChatGPT and chunkx for more personalized and continuous education

It’s obvious that digital training is becoming increasingly important to your business. However, it’s also clear that without sustained support, the ever-increasing amount of learning content will overwhelm you and not sustainably embed your knowledge.
That’s why it’s time to leverage technologies like ChatGPT and other smart tools to make employee development more continuous and personalized.

Want to learn more? Contact us for a personalized consultation and let’s redefine your organization’s employee development together!

Also take the opportunity to subscribe to our newsletter and never miss a technological update again. By the way, we’re also on LinkedIn!