Data integration
Data integration is the process of combining data from multiple sources into a coherent form for consistent access, processing, or analysis.
Knowledge Graphs and LLMs in Action
The process of combining data from multiple sources into a coherent and consistent representation.
- How it is used
- Supports construction and analysis of knowledge graphs from biomedical and other multisource data.
- How deep it goes
- Explains transformation, reconciliation, merging, inference, and analysis while deferring detailed implementation to individual pipelines.
- Examples
- Uses drug discovery, clinical knowledge graphs, precision medicine, and patient journey mapping as concrete applications.
- What you can do after
- Apply integration patterns to build coherent biomedical graphs for retrieval, hypothesis generation, and clinical decision support.
Read how Knowledge Graphs and LLMs in Action explains data integration →
Data for All
The combination of data from multiple sources or categories into a coherent, accessible form.
- How it is used
- Shows how combining personal and external data supports targeting, and how future data services might serve individuals’ objectives.
- How deep it goes
- Explains combinations through everyday examples and business aims, without giving technical integration steps.
- Examples
- Uses location, browsing, and transaction data, plus combined in-store and online grocery purchases.
- What you can do after
- Evaluate/understand whose objectives a combined data collection serves and how grouping choices could affect its value.
The Art of AI Product Development
Data integration is the combining and coordinating of data from multiple sources, formats, or repositories so it can be processed consistently.
- How it is used
- Supports AI adoption by connecting existing organizational data and expertise to products, models, and user workflows.
- How deep it goes
- Covers scattered data, format differences, cleanup, governance, infrastructure, and retrieval-augmented generation, but not implementation code.
- Examples
- Uses legacy analytics platforms, sustainability reporting, wikis, knowledge bases, internal documents, and custom language-model applications.
- What you can do after
- Apply it via retrieval-augmented generation to produce more relevant, current, and context-aware language-model responses.
Read how The Art of AI Product Development explains data integration →
Delivering Machine Learning Projects: From design to deployment
Data integration is the combination of data from multiple sources into a coherent structure or access layer.
- How it is used
- Structures heterogeneous source data into accessible resources for machine-learning modeling.
- How deep it goes
- Moves from ingestion through cleaning, feature creation, access, serving, and documentation, while flagging statistical and engineering risks.
- Examples
- Uses single tables, intermediate stores, SQL queries, large files, APIs, and data streams as integration outputs.
- What you can do after
- Build it from scratch as a documented, access-controlled data resource that modeling teams can self-serve.
Read how Delivering Machine Learning Projects: From design to deployment explains data integration →
First-Party Data Activation
Data integration is the process of combining data from disparate sources into a coherent, accessible whole.
- How it is used
- Unifies fragmented customer and platform data for segmentation, campaign decisions, and privacy-conscious collaboration.
- How deep it goes
- Explains business rationale, pipeline safeguards, lakehouse architecture, and clean-room matching without descending into implementation procedures.
- Examples
- Uses cloud migration, retail channel unification, and anonymized brand-publisher audience matching as concrete integration examples.
- What you can do after
- Apply it to build unified audiences, reduce duplicate or missed records, and improve targeting while preserving user privacy.
Read how First-Party Data Activation explains data integration →
Related concepts
- data sourceuses · A data source is an origin, system, repository, or process from which data is obtained for use or processing.
- structured datauses · Structured data is information organized according to an explicit schema or predictable fields, types, records, or relationships for consistent machine processing.
- language modelcontrasts with · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- intelligent advisory systemused by · An intelligent advisory system is an intelligent system that provides recommendations or alerts to support human decision-making without independently taking action.
- entity resolutionhas part · Entity resolution is the process of determining which records or mentions refer to the same real-world entity despite differences in their representations.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.