Khalifeh AlJaddaPh.D. in computer science from the University of Georgia (UGA)
Khalifeh AlJadda holds Ph.D. in computer science from the University of Georgia (UGA), with a specialization in machine learning. He has experience implementing large-scale, distributed machine learning algorithms to solve challenging problems in domains ranging from Bioinformatics to search and recommendation engines. He is the lead data scientist on the search data science team at CareerBuilder, which is one of the largest job boards in the world. He was in charge of the data science effort to design and implement the backend of CareerBuilder’s language-agnostic semantic search engine leveraging Apache Spark and the Hadoop ecosystem. Recently, his team has been working on building a new AI-based recommendation engine using cutting-edge technologies in data science and Big Data. Khalifeh is the founder and organizer of the Southern Data Science Conference (https://www.southerndatascience.com) which is the major data science conference in Atlanta that aims to promote data science to the Southern companies and schools. Also, Khalifeh is a co-founder of ATLytiCS (www.atlytics.org) a non-profit organization that aims to use the data science and analytics to serve the society. Khalifeh is a frequent public speaker on topics related to data science, machine learning, semantic search, and big data analytics. For more information, please visit his website (www.aljadda.com).
Title and abstract
Reflected Intelligence: Evolving self-learning Information Retrieval Systems
In the big data era, search and recommendation engines have become the primary mechanisms through which users both actively find and passively discover useful information. As such, it has never been more critical for these data systems to be able to deliver targeted, relevant results that fully match a user’s intent.
In this presentation, we’ll talk about evolving self-learning search and recommendation systems which are able to accept user queries, deliver relevance-ranked results, and iteratively learn from the users’ subsequent interactions to continually deliver a more relevant experience. Such a self-learning system leverages reflected intelligence to consistently improve its understanding of the content (documents and queries), the context of specific users, and the collective feedback from all prior user interactions with the system. Through iterative feedback loops, such a system can leverage user interactions to learn the meaning of important phrases and topics within a domain, identify alternate spellings and disambiguate multiple meanings of those phrases, learn the conceptual relationships between phrases, and even learn the relative importance of features to automatically optimize its own ranking algorithms on a per-query, per-category, or per-user/group basis.
We will cover some of the core technologies that enable such a system to be built (Apache Lucene/Solr, Apache Spark, Apache Hadoop, cloud computing), and will walk through some practical examples of how such a reflected intelligence system has been built and is being leveraged in a real-world implementation.