Abstract
Ranked search results and recommendations have become the main mechanism by which we find content, products, places, and people online. With hiring, selecting, purchasing, and dating being increasingly mediated by algorithms, rankings may determine career and business opportunities, educational placement, access to benefits, and even social and reproductive success. It is therefore of societal and ethical importance to ask whether search results can demote, marginalize, or exclude individuals of unprivileged groups or promote products with undesired features. In this paper we present FairSearch, the first fair open source search API to provide fairness notions in ranked search results. We implement two algorithms from the fair ranking literature, namely FA*IR (Zehlike et al., 2017) and DELTR (Zehlike and Castillo, 2018) and provide them as stand-alone libraries in Python and Java. Additionally we implement interfaces to Elasticsearch for both algorithms, that use the aforementioned Java libraries and are then provided as Elasticsearch plugins. Elasticsearch is a well-known search engine API based on Apache Lucene. With our plugins we enable search engine developers who wish to ensure fair search results of different styles to easily integrate DELTR and FA*IR into their existing Elasticsearch environment.
Highlights
With the volume of information increasing at a frenetic pace, ranked search results have become the main mechanism by which we find
In rankings disparate impact translates into differences in exposure [7] or inequality of attention across groups, which are to be understood as systematic differences in access to economic or social opportunities
In this paper we present FairSearch, the first fair open source search API that implements two well-known methods from the literature, namely FA*IR [9] and DELTR [10]
Summary
With the volume of information increasing at a frenetic pace, ranked search results have become the main mechanism by which we find. In this paper we present FairSearch, the first fair open source search API that implements two well-known methods from the literature, namely FA*IR [9] and DELTR [10]. For both algorithms the implementation is provided as a stand-alone Java and Python library, as well as interfaces for Elasticsearch, a popular, welltested search engine, which is used by many big brands such as Amazon, Netflix and Facebook. By providing the algorithms as stand-alone libraries in Python and Java and for Elasticsearch we make the on-going research on fair machine learning accessible and ready-to-use for a broad community of professional developers and researchers, those working in the realm of humancentric and socio-technical systems, as well as sharing economy platforms
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
