Mangaki
[Mangaki]
Within a set of search results, what should you do to find the optimal solution for not just a single user but a group? Mangaki is building an open source library for privacy-preserving group recommendations of items. While many content providers suggest recommendations at a personal level, these are often directed to a single user, or are restricted to a generic “family” category. Whenever say a group of friends want to watch a movie, it is often hard to decide what to watch, because people can have really different tastes.
Recommendations are also very privacy-sensitive. A straightforward way might be to share our complete viewing history, but that certainly can lead to embarrassing and awkward situations. So how can we collectively compute a list of relevant items without disclose all of our data unencrypted. The Mangaki project is making an open source library for group recommendations that works in a scalable and distributed way.
- The project's own website: https://mangaki.fr
Why does this actually matter to end users?
Search and discovery is one of the most important and essential use cases of the internet. When you are in school and need to give a presentation, when you are looking for a job, trying to promote your business or finding relevant commercial or public services you need, most of the time you will turn to the internet and more importantly the search bar in your browser to find answers. Searching information and making sure your name, company or idea can be discovered is crucial for users, but they actually have little control over this. Search engines set the terms for what results you see, how your website can be discovered and what information is logged about your searches. What terms are set remains obscure for users and they can only follow the rules laid out for them, instead of deciding on their own what, where and how to find the information they are looking for.
Online search basically is a black box: you enter your question and get an answer, or optimize your site to to end up in the top ten results, but no one has actual control over how it all works. Not only does this make us dependent on search providers, it can (and does) jeopardize your privacy, from the actual query itself to all sorts of sensitive metadata you might leak (other sites you visited, your IP address, other online accounts, etcetera).
So how do we regain control over how we search online? One way to do this is to build transparent, user-centric and privacy-friendly alternatives to popular search solutions. This is especially important for technologies that handle sensitive, personal information, like recommendation systems. Think of 'customers have also bought'. Online sellers and service providers are eager to gather this information as it can make their advertisements and site offerings more attractive. Unfortunately users run the risk of having this data leaked to the internet (which is especially risky when it is of a medical, sexual or religious nature) or resold to shady profile brokers. This project aims to create open source building blocks for group recommendations of items.
Run by Mangaki/Inria
This project was funded through the NGI0 Discovery Fund, a fund established by NLnet with financial support from the European Commission's Next Generation Internet programme, under the aegis of DG Communications Networks, Content and Technology under grant agreement No 825322.