- Duration: 3 days
- Skill-level: Foundation-level Relevant Search skills for Intermediate skilled team members. This is not a basic class.
- Targeted Audience: This course is geared for those who wants to know how to return engaging search results to your users, helping you understand and leverage the internals of Lucene-based search engines.
- Hands-on Learning: This course is approximately 50% hands-on lab to 50% lecture ratio, combining engaging lecture, demos, group activities and discussions with machine-based student labs and exercises. Student machines are required.
- Delivery Format: This course is available for onsite private classroom presentation.
- Customizable: This course may be tailored to target your specific training skills objectives, tools of choice and learning goals.
Relevant Search demystifies the subject and shows you that a search engine is a programmable relevance framework. You’ll learn how to apply Elasticsearch or Solr to your business’s unique ranking problems. The course demonstrates how to program relevance and how to incorporate secondary data sources, taxonomies, text analytics, and personalization. In practice, a relevance framework requires softer skills as well, such as collaborating with stakeholders to discover the right relevance requirements for your business. By the end, you’ll be able to achieve a virtuous cycle of provable, measurable relevance improvements over a search product’s lifetime.
Working in a hands-on learning environment, led by our Relevant Search expert instructor, students will learn about and explore:
- You’ll learn how to apply Elasticsearch or Solr to your business’s unique ranking problems.
- demonstrates how to program relevance and how to incorporate secondary data sources, taxonomies, text analytics, and personalization
Topics Covered: This is a high-level list of topics covered in this course. Please see the detailed Agenda below
- Techniques for debugging relevance
- Applying search engine features to real problems
- Using the user interface to guide searchers
- A systematic approach to relevance
- A business culture focused on improving search
Audience & Pre-Requisites
This course is designed for those who wants to know how to return engaging search results to your users, helping you understand and leverage the internals of Lucene-based search engines.
Pre-Requisites: Students should have familiar with
For developers trying to build smarter search with Elasticsearch or Solr.
Course Agenda / Topics
- The search relevance problemfree
- Your goal: gaining the skills of a relevance engineer
- Why is search relevance so hard?
- Gaining insight from relevance research
- How do you solve relevance?
- More than technology: curation, collaboration, and feedback
- Search—under the hood
- Search 101
- Search engine data structures
- Indexing content: extraction, enrichment, analysis, and indexing
- Document search and retrieval
- Debugging your first relevance problem
- Applications to Solr and Elasticsearch: examples in Elasticsearch
- Our most prominent data set: TMDB
- Examples programmed in Python
- Your first search application
- Debugging query matching
- Debugging ranking
- Solved? Our work is never over!
- Taming tokensfree
- Tokens as document features
- Controlling precision and recall
- Precision and recall—have your cake and eat it too
- Analysis strategies
- Basic multifield search
- Signals and signal modeling
- TMDB—search, the final frontier!
- Signal modeling in field-centric search
- Term-centric search
- What is term-centric search?
- Why do you need term-centric search?
- Performing your first term-centric searches
- Solving signal discordance in term-centric search
- Combining field-centric and term-centric strategies: having your – cake and eating it too
- Shaping the relevance function
- What do we mean by score shaping?
- Boosting: shaping by promoting results
- Filtering: shaping by excluding results
- Score-shaping strategies for satisfying business needs
- Providing relevance feedback
- Relevance feedback at the search box
- Relevance feedback while browsing
- Relevance feedback in the search results listing
- Designing a relevance-focused search application
- Yowl! The awesome new start-up!
- Gathering information and requirements
- Designing the search application
- Deploying, monitoring, and improving
- Knowing when good is good enough
- The relevance-centered enterprise
- Feedback: the bedrock of the relevance-centered enterprise
- Why user-focused culture before data-driven culture?
- Flying relevance-blind
- Relevance feedback awakenings: domain experts and expert users
- Relevance feedback maturing: content curation
- Relevance streamlined: engineer/curator pairing
- Relevance accelerated: test-driven relevance
- Beyond test-driven relevance: learning to rank
- Semantic and personalized search
- Personalizing search based on user profiles
- Personalizing search based on user behavior
- information back to the search index
- Basic methods for building concept search
- Building concept search using machine learning
- The personalized search—concept search connection
- Recommendation as a generalization of search
- Best wishes on your search relevance journey