Research & Develop

Recommender-System Software Libraries & APIs

There is a plethora of software libraries and APIs that often implement dozens of recommendation algorithms. We define a 'recommender-system software library' as e.g. a JAVA or Python library that you can easily integrate into your own application to run recommendation algorithms. Nevertheless, you still do need some recommender-system and programming knowledge to store data...

Read more ...

Datasets

There are a plethora of recommender-system datasets, and, more generally, almost every machine learning dataset can be used for recommendation systems, too. The de-facto standard dataset for recommendations is probably the MovieLens dataset (which exists in multiple variations). Based on a small study that we conducted, 40% of all research papers at the ACM Recommender...

Read more ...

Consultants & Freelance Developers

When getting stuck in your work, a consultant or freelance developer may help. On this page, we provide an overview of consultants and freelance developers in the field of recommender systems. Details yet to come...

Read more ...

Computing Resources

Running recommender-system experiments may require significant computing resources. Especially memory-based approaches like kNN might need more memory than a normal desktop computer offers. Luckily, many organisations offer free or cheap (cloud) computing resources, though often limited in their free versions Cloud GPUs https://vast.ai/ claims to reduce GPU costs by factor 3-5 as they don´t offer...

Read more ...

Competitions, Shared Tasks & Living Labs

To test your skills in recommender-system development and research, competitions, shared tasks and living labs are ideal. Details yet to come...

Read more ...

Recommendations-As-a-Service (RaaS)

While recommender-system software libraries and APIs support you in developing a recommender system, a Recommender-System As-a-Service (RaaS) does all the work for you. Typically, you can integrate a recommender system into e.g. your e-commerce website or blog with a few clicks or lines of code. A RaaS comes with some compromises relating to flexibility, control...

Read more ...

State-of-the-Art Algorithms

"What are state-of-the-art recommendation algorithms?" is a question that should be a no-brainer to answer for any recommender-system researcher and developer. However, the answer is typical "I don't know, at least not for sure". The recommender-system community faces a reproducibility crisis, which makes it almost impossible to say what algorithms are truly state-of-the-art. In a...

Read more ...

Multi-Collections

There are a few sources on the Web where you find great collections of datasets, code, and advice. Some of them are listed here, let us know if something is missing. Microsoft Recommenders A nice and relatively recent collection of recommender-system tools and best practice guidelines maintained by different persons at Microsoft. To the best...

Read more ...