A
term
A/A test
An A/A test splits users into two groups that get the same experience, to check that your experimentation…
term
A/B test
An A/B test compares two versions of something by showing each to a random group of users and…
tool
AB Tasty
AB Tasty is an experimentation and personalisation platform for web and product teams.
term
Ad hoc analysis
Ad hoc analysis is a one-off investigation to answer a specific question, rather than a recurring report.
tool
Adobe Analytics
Adobe Analytics is an enterprise web analytics platform from Adobe, part of Adobe Experience Cloud.
tool
Adobe Target
Adobe Target is Adobe testing and personalisation tool, part of Adobe Experience Cloud.
term
Agent harness
An agent harness is everything around a model that makes an agent useful and safe: tools, permissions, memory,…
term
Agentic workflow
An agentic workflow is a process in which an AI system plans steps, uses tools and checks its…
term
AI agent
An AI agent is a system that uses a language model to pursue a goal by planning steps…
term
AI evaluations (evals)
AI evaluations are tests that measure how well an AI system performs on realistic tasks.
term
AI governance
AI governance is the set of policies, roles and controls that make sure AI is used safely, legally…
term
AI guardrails
Guardrails are the rules and checks that keep an AI system within safe and intended behaviour.
term
AI observability
AI observability is tracking what an AI system does in production: inputs, outputs, tool calls, cost, latency and…
tool
Airbyte
Airbyte is an open-source data integration platform with a large catalogue of connectors.
tool
Amazon Redshift
Amazon Redshift is AWS data warehouse service for large-scale analytics.
tool
Amazon S3
Amazon S3 is AWS object storage, widely used as the foundation of data lakes.
tool
Amazon Web Services (AWS)
AWS is Amazon cloud platform, offering storage, compute and data services such as S3 and Redshift.
tool
Amplitude
Amplitude is a product analytics platform for understanding behaviour, retention and growth.
term
Analytics audit
An analytics audit is a structured review of your tracking set-up to find missing, broken or misleading data.
term
Analytics engineering
Analytics engineering is applying software engineering practices to analytics: version control, testing, documentation and modular code.
tool
Apache Airflow
Apache Airflow is an open-source platform for authoring, scheduling and monitoring data workflows.
tool
Apache Kafka
Apache Kafka is an open-source platform for streaming events between systems in real time.
term
API
An API (application programming interface) is a defined way for software systems to exchange data and commands.
term
Attribution
Attribution is the process of assigning credit for a conversion to the marketing touchpoints that led to it.
term
Audience
An audience is a group of users defined by shared behaviour or attributes, which you can analyse or…
B
term
Backfill
A backfill loads or reprocesses historical data, for example after adding a new source or fixing a bug.
term
Batch vs streaming
Batch processing handles data in scheduled chunks, while streaming processes it continuously as it arrives.
term
Bayesian statistics
Bayesian statistics expresses results as the probability that a variant is better, updated as data arrives.
term
Bot traffic
Bot traffic is non-human traffic generated by automated programs such as crawlers, scrapers and fraud scripts.
term
Bounce rate
Bounce rate is the percentage of sessions in which the visitor did not engage with your site.
C
term
Calculated field
A calculated field is a new value computed from existing fields inside a BI tool, such as profit…
term
Call to action (CTA)
A call to action is a prompt that tells visitors what to do next, such as a button…
term
Canary release
A canary release exposes a new version to a small group of users to detect problems before everyone…
term
CCPA / CPRA
The CCPA, expanded by the CPRA, is California privacy law giving residents rights over their personal information.
term
Change data capture (CDC)
Change data capture tracks inserts, updates and deletes in a source database and replicates only those changes.
term
Channel grouping
Channel grouping organises traffic sources into marketing channels such as organic search, paid search, email and social.
term
Chatbot
A chatbot is a software assistant that converses with users in text or voice.
tool
ChatGPT
ChatGPT is OpenAI conversational AI assistant, built on its GPT family of models.
term
Chunking
Chunking is splitting documents into smaller pieces so they can be indexed and retrieved for AI systems.
term
Churn rate
Churn rate is the percentage of customers or users who stop using a product or cancel within a…
tool
Claude
Claude is a family of AI models and assistants from Anthropic.
term
Click ID (gclid)
A click ID is a unique identifier added to a landing page URL by an ad platform, such…
term
Client-side testing
Client-side testing changes the page in the visitor browser using JavaScript, typically with a visual editor.
term
Cohort analysis
Cohort analysis groups users by a shared starting point, such as sign-up week, and tracks how their behaviour…
term
Columnar storage
Columnar storage stores data by column rather than by row, which makes analytical queries much faster.
term
Company brain
A company brain is a private, governed knowledge layer over a company documents, tools and data that people…
term
Confidence interval
A confidence interval is a range of values that likely contains the true effect, given the data.
term
Consent management platform (CMP)
A consent management platform collects and records visitor consent choices and tells your tags what they are allowed…
term
Consent Mode
Consent Mode lets Google tags adjust their behaviour based on whether a visitor has given consent for analytics…
term
Context window
The context window is the amount of text a language model can consider at once, including your instructions,…
term
Conversion
A conversion is a visitor completing a valuable action, such as buying, signing up or requesting a demo.
term
Conversion rate
Conversion rate is the percentage of visitors or sessions that complete a desired action.
term
Conversions API
A conversions API sends conversion events from your server directly to an ad platform, such as Meta, instead…
tool
Convert
Convert is an A/B testing platform known for privacy features and fast, lightweight testing.
term
Cookie
A cookie is a small file stored in the browser that lets a website remember information about a…
term
Cross-device tracking
Cross-device tracking connects the activity of one person across phones, tablets and computers.
term
Cross-domain tracking
Cross-domain tracking lets analytics treat a visit that spans several domains as one session.
term
CUPED
CUPED reduces variance in experiments by using pre-experiment data about each user, so tests reach conclusions faster.
term
Custom dimension
A custom dimension is an extra attribute you register in your analytics tool so it can be used…
term
Custom metric
A custom metric is a numeric value you register in your analytics tool, such as a score, a…
term
Customer acquisition cost (CAC)
Customer acquisition cost is the average spend needed to win a new customer.
term
Customer data platform (CDP)
A customer data platform collects customer data from many sources into unified profiles that other tools can use.
term
Customer lifetime value (LTV)
Customer lifetime value is the total revenue or profit you expect from a customer over the whole relationship.
D
tool
Dagster
Dagster is an orchestration platform that models data pipelines in terms of the data assets they produce.
term
Dashboard
A dashboard is a visual display of the most important metrics, designed to be understood at a glance.
term
Data
Data is recorded information, such as numbers, text or events, that can be stored and analysed.
term
Data catalog
A data catalog is an organised inventory of your data assets, with descriptions, owners and lineage.
term
Data contract
A data contract is an agreement between data producers and consumers about the structure and meaning of a…
term
Data cost optimization
Data cost optimization is reducing the cost of storing, moving and querying data without hurting the business.
term
Data governance
Data governance is the set of policies, roles and processes that keep data accurate, secure and used appropriately.
term
Data grain
The grain of a table is what a single row represents, such as one order line or one…
term
Data ingestion
Data ingestion is the process of bringing data from sources into a storage or analytics system.
term
Data lake
A data lake is a store that holds large amounts of raw data in its original format, until…
term
Data lakehouse
A data lakehouse combines the low-cost storage of a data lake with the management and query features of…
term
Data latency
Data latency is the delay between something happening and it being available for analysis.
term
Data layer
The data layer is a JavaScript object on your site that holds structured information for your tag manager…
term
Data lineage
Data lineage shows where data comes from and how it is transformed on its way to a report.
term
Data literacy
Data literacy is the ability to read, question and use data to make decisions.
term
Data mart
A data mart is a focused subset of a warehouse built for one team or subject, like marketing…
term
Data masking
Data masking hides or obscures sensitive values, so people can work with data without seeing personal details.
term
Data mesh
Data mesh is an approach where business domains own and publish their own data as products, supported by…
term
Data modeling
Data modeling is designing how data is structured in a warehouse so it is easy and consistent to…
term
Data observability
Data observability is monitoring the health of data and pipelines, so problems are found before users notice.
term
Data orchestration
Data orchestration coordinates and schedules the steps of data workflows, handling dependencies, retries and alerts.
term
Data pipeline
A data pipeline is an automated process that moves data from one or more sources to a destination,…
term
Data product
A data product is a dataset or model packaged for reuse, with an owner, documentation, quality guarantees and…
term
Data quality
Data quality describes how accurate, complete, consistent and timely your data is.
term
Data replication
Data replication copies data from one system to another, to keep a second copy up to date.
term
Data retention
Data retention policies define how long different data is kept before it is deleted or archived.
term
Data sampling
Data sampling is when a tool analyses only a subset of your data and extrapolates the results to…
term
Data storytelling
Data storytelling is combining data, visuals and narrative to explain what is happening and what to do about…
term
Data stream
A data stream is a source of data flowing into a GA4 property, such as a website, an…
term
Data thresholding
Data thresholding hides some report data to protect user privacy, usually when numbers are very small.
term
Data visualization
Data visualization is presenting data in charts, maps and graphics so patterns are easy to see.
term
Data warehouse
A data warehouse is a central database designed for analysis, where data from many systems is stored and…
term
Data warehouse migration
A warehouse migration moves data, models and reports from one warehouse platform to another.
term
Data-driven attribution
Data-driven attribution uses statistical models on real conversion paths to assign credit to each touchpoint.
tool
Databricks
Databricks is a data and AI platform built around the lakehouse approach and Apache Spark.
tool
Dataform
Dataform is a Google Cloud service for developing and orchestrating SQL transformations in BigQuery.
tool
dbt
dbt is a tool for transforming data in a warehouse using SQL, with version control, testing and documentation.
term
dbt macro
A dbt macro is a reusable piece of SQL logic written with Jinja templating.
term
dbt snapshot
A dbt snapshot records changes to a mutable table over time, producing a history of each row.
term
dbt test
A dbt test is an automated check that a model meets expectations, such as unique, not null or…
term
Dimension
A dimension is an attribute used to slice or group metrics, such as country, device or channel.
term
Direct traffic
Direct traffic is visits where the source could not be determined, often because the visitor typed the address…
term
Drill-down
Drill-down lets you move from a summary to the underlying detail, for example from country to city to…
E
term
Ecommerce tracking
Ecommerce tracking records shopping behaviour, such as product views, add-to-cart actions and purchases, in your analytics tool.
term
Effect size
Effect size is the magnitude of a difference between variants, not just whether it exists.
term
ELT (extract, load, transform)
ELT loads raw data into the warehouse first and transforms it there afterwards, using the warehouse engine.
term
Embedded analytics
Embedded analytics puts charts and dashboards inside your own product or customer portal.
term
Embeddings
Embeddings are numerical representations of text or other data that capture meaning, so similar things are close together.
term
Engagement rate
Engagement rate is the share of sessions that were engaged, meaning they lasted long enough, included a conversion…
term
Enhanced conversions
Enhanced conversions send hashed first-party data, like an email address, with a conversion so Google can match it…
term
Enhanced measurement
Enhanced measurement is a GA4 option that automatically records common interactions such as scrolls, outbound clicks, site search…
term
Entity resolution
Entity resolution is determining whether different records refer to the same real-world entity, such as a customer or…
tool
Eppo
Eppo is an experimentation platform built to run directly on your data warehouse.
term
ETL (extract, transform, load)
ETL is a process that extracts data from sources, transforms it, and then loads it into a destination…
term
Event
An event is a single recorded user interaction, such as a page view, click, scroll or purchase.
term
Event parameter
A parameter is an extra piece of information attached to an event, such as a product name, a…
term
Experiment velocity
Experiment velocity is how many experiments a team completes in a period.
term
Experimentation program
An experimentation program is the organisation, process and tooling that lets a company run experiments consistently.
term
Exposure logging
Exposure logging records the moment a user is actually shown a variant, so analysis only includes users who…
F
term
Feature flag
A feature flag is a switch in code that turns a feature on or off for some or…
term
Fine-tuning
Fine-tuning is training an existing model further on your own examples, to specialise its behaviour or style.
tool
Firebase
Firebase is Google app development platform, which includes analytics, crash reporting, remote config and more.
term
First-party data
First-party data is information you collect directly from your own customers and visitors.
tool
Fivetran
Fivetran is a managed ELT service with connectors for many SaaS tools and databases.
term
Flash of original content (FOOC)
FOOC is when visitors briefly see the original page before a client-side test applies the variant.
term
Form analytics
Form analytics measures how users interact with forms, including where they hesitate, correct entries or abandon.
term
Frequentist statistics
Frequentist statistics judges evidence by how likely the data would be if there were no real effect.
tool
FullStory
FullStory is a digital experience analytics platform known for session replay and behavioural insights.
term
Function calling (tool use)
Function calling lets a language model request that your code run a defined tool, such as a database…
term
Funnel analysis
Funnel analysis measures how many users move through each step of a process, such as checkout, and where…
G
term
GA4 BigQuery export
The GA4 BigQuery export sends your raw GA4 event data to a BigQuery dataset for custom analysis.
term
GA4 Explorations
Explorations are GA4 free-form analysis tools for building custom reports such as funnels, paths and segment overlaps.
term
GDPR
The GDPR is the European Union data protection regulation that governs how personal data of people in the…
tool
Gemini
Gemini is Google family of AI models and assistant, available across Google products and through APIs.
tool
Google Ads
Google Ads is Google online advertising platform, covering search, display, video and more.
tool
Google Analytics (GA4)
Google Analytics 4 is Google web and app analytics platform, built around events and the successor to Universal…
term
Google Analytics Parallel Tracking
Parallel Tracking sends a second copy of your GA4 hits to your own data pipeline, so you can…
tool
Google BigQuery
BigQuery is Google serverless cloud data warehouse, popular for analytics and a common destination for GA4 data.
tool
Google Cloud
Google Cloud is Google cloud computing platform, home to BigQuery, Cloud Storage and many data and AI services.
tool
Google Optimize (sunset)
Google Optimize was Google free A/B testing tool, discontinued on 30 September 2023.
tool
Google Search Console
Google Search Console is a free tool that shows how your site performs in Google Search.
term
Google signals
Google signals is a GA4 feature that uses data from signed-in Google users who consented to ads personalisation,…
tool
Google Tag Manager
Google Tag Manager is a free tag management system for deploying and managing tracking tags on websites and…
tool
GrowthBook
GrowthBook is an open-source experimentation and feature flagging platform that works with your own data warehouse.
term
gtag.js
gtag.js is the Google tag, a JavaScript library that sends data to Google Analytics, Google Ads and other…
term
Guardrail metric
A guardrail metric is a measure you monitor during a test to make sure the change does not…
H
term
Hallucination
A hallucination is when an AI model produces confident but incorrect or invented information.
tool
Heap
Heap is a product analytics platform known for autocapturing user interactions.
term
Heatmap
A heatmap is a visual overlay that shows where users click, move and scroll on a page.
term
Holdout group
A holdout group is a set of users deliberately kept from a change or campaign, to measure its…
tool
Hotjar
Hotjar is a behaviour analytics tool offering heatmaps, session recordings and surveys.
tool
HubSpot
HubSpot is a CRM and marketing platform used for contacts, deals, email and automation.
term
Human in the loop
Human in the loop means a person reviews or approves an AI output or action before it takes…
I
term
Idempotency
An idempotent process gives the same result no matter how many times it runs.
term
Identity resolution
Identity resolution is matching records from different sources to the same person or household.
term
Impression
An impression is each time an ad, a listing or a piece of content is displayed to a…
term
Incremental model
An incremental model processes only new or changed data on each run instead of rebuilding the whole table.
term
Incrementality
Incrementality is the extra outcome caused by a marketing activity, compared with what would have happened without it.
term
Infrastructure as code
Infrastructure as code defines cloud resources in version-controlled files, so environments are reproducible and reviewable.
term
Intelligent Tracking Prevention (ITP)
ITP is Safari technology that limits cross-site tracking and shortens the lifetime of some cookies.
term
ISO/IEC 42001
ISO/IEC 42001 is an international standard for an AI management system.
K
tool
Kameleoon
Kameleoon is an experimentation and personalisation platform covering both web and feature experimentation.
term
Key event
A key event is an event you mark as especially important to your business. In GA4 it replaced…
term
Keyword
A keyword is a word or phrase that people type into a search engine, and that you target…
term
Kill switch
A kill switch is a feature flag that can instantly turn a feature off in production.
term
Knowledge graph
A knowledge graph represents entities and the relationships between them, such as customers, products and orders.
term
KPI (key performance indicator)
A KPI is a measurable value that shows how well you are achieving an important business objective.
L
term
Landing page
A landing page is the first page a visitor sees in a session.
term
Large language model (LLM)
A large language model is an AI system trained on large amounts of text that can understand and…
term
Last-click attribution
Last-click attribution gives 100 percent of the credit for a conversion to the final touchpoint before it.
tool
LaunchDarkly
LaunchDarkly is a feature management platform used to control feature rollouts with flags.
term
Leading vs lagging indicators
Leading indicators predict future results, while lagging indicators confirm results that have already happened.
term
Live connection vs extract
A live connection queries the warehouse every time a dashboard loads; an extract is a stored copy refreshed…
tool
Looker
Looker is Google Cloud business intelligence platform, built on a code-based semantic layer called LookML.
tool
Looker Studio
Looker Studio, formerly Data Studio, is Google free tool for building interactive reports and dashboards.
tool
LookML
LookML is the modelling language of Looker, used to define data models, dimensions and measures.
M
term
Marketing mix modeling (MMM)
Marketing mix modeling uses statistics on aggregated data to estimate how each channel contributes to sales.
term
Master data management (MDM)
MDM is managing the core entities of a business, like customers and products, so that one trusted version…
term
Materialized view
A materialized view stores the precomputed result of a query, so reports read it quickly instead of recomputing…
tool
Matomo
Matomo is an open-source web analytics platform, available self-hosted or as a cloud service, with a strong focus…
term
Measurement plan
A measurement plan documents what you will track, why, and how each event and parameter is defined.
term
Measurement Protocol
The Measurement Protocol lets you send events to GA4 directly from a server over HTTP, instead of from…
tool
Meta Pixel
The Meta Pixel is a snippet that records visitor actions for Meta (Facebook and Instagram) advertising measurement and…
tool
Metabase
Metabase is an open-source business intelligence tool for simple, self-serve exploration of data.
term
Metadata
Metadata is data about data: descriptions, owners, types, freshness and lineage.
term
Metric
A metric is a quantitative measure of performance, such as revenue, conversion rate or active users.
term
Metric tree
A metric tree breaks a top-level metric down into the input metrics that drive it.
tool
MetricFlow
MetricFlow is the semantic layer technology used by dbt to define metrics and generate queries.
term
Micro conversion
A micro conversion is a smaller step that signals progress towards a main conversion, such as watching a…
tool
Microsoft Azure
Azure is Microsoft cloud platform, with data services such as Synapse, Data Lake Storage and Fabric.
term
Minimum detectable effect (MDE)
The MDE is the smallest change your test is designed to reliably detect.
tool
Mixpanel
Mixpanel is a product analytics tool focused on user behaviour, funnels, retention and cohorts.
term
Model Context Protocol (MCP)
MCP is an open standard that lets AI applications connect to external tools and data sources in a…
term
Model drift
Model drift is when an AI or machine learning system gets worse over time because the world or…
term
Multi-agent system
A multi-agent system uses several AI agents with different roles that collaborate on a task.
term
Multi-armed bandit
A multi-armed bandit shifts traffic towards better-performing variants while a test is still running.
term
Multi-touch attribution
Multi-touch attribution spreads credit for a conversion across several touchpoints in the customer journey.
term
Multiple comparisons problem
The multiple comparisons problem is that testing many metrics or variants raises the chance of at least one…
term
Multivariate test
A multivariate test changes several elements at once and measures the effect of every combination.
N
term
New vs returning users
New users are visitors who are recorded for the first time; returning users have been seen before.
term
North Star metric
A North Star metric is the single measure that best captures the value your product delivers to customers.
term
Novelty effect
The novelty effect is a temporary change in behaviour caused simply by something being new.
O
term
Offline conversions
Offline conversions are sales or leads that happen outside your website, such as phone orders or CRM deals,…
term
OLAP
OLAP (online analytical processing) systems are built for fast analysis of large volumes of historical data.
term
OLAP cube
An OLAP cube is a pre-aggregated, multidimensional data structure that makes slicing and dicing fast.
term
OLTP
OLTP (online transaction processing) databases are built to run applications, handling many small reads and writes quickly.
tool
Omni
Omni is a business intelligence platform that combines a governed semantic model with flexible exploration.
term
On-site polls
On-site polls are short surveys shown to visitors on your website to learn why they behave the way…
term
One-tailed vs two-tailed test
A one-tailed test looks for an effect in one direction only; a two-tailed test looks for a difference…
tool
Optimizely
Optimizely is a digital experience platform known for web experimentation, feature experimentation and personalisation.
term
Organic search
Organic search is traffic from unpaid results on search engines.
P
term
P-value
A p-value is the probability of seeing a result at least as extreme as yours if there were…
term
Pageview
A pageview is recorded each time a page of your website is loaded or viewed.
term
Partitioning and clustering
Partitioning splits a large table into segments, and clustering sorts data within them, so queries read less data.
term
Peeking problem
Peeking is checking results repeatedly and stopping the moment they look significant, which inflates false positives.
tool
Pendo
Pendo is a product experience platform combining analytics with in-app guides and feedback.
term
Personalization
Personalization tailors content or offers to individual users or segments, based on their behaviour or attributes.
term
Personally identifiable information (PII)
PII is any data that can identify a person, such as a name, email address, phone number or…
term
Pivot table
A pivot table summarises data by letting you drag fields into rows, columns and values.
tool
PostHog
PostHog is an open-source product analytics platform that also includes session replay, feature flags and experiments.
tool
Power BI
Power BI is Microsoft business intelligence platform for modelling data and building reports and dashboards.
term
Practical significance
Practical significance asks whether a measured effect is large enough to matter to the business.
term
Product analytics
Product analytics studies how people use a digital product, to improve features, onboarding and retention.
term
Progressive delivery
Progressive delivery releases a change to a small share of users first and expands gradually while monitoring results.
term
Prompt engineering
Prompt engineering is the craft of writing instructions and context that get consistently good results from a language…
term
Prompt injection
Prompt injection is an attack where malicious text tricks an AI system into ignoring its instructions or leaking…
R
term
Randomization unit
The randomization unit is what gets assigned to a variant: a user, a session, an account or a…
term
Real-time analytics
Real-time analytics analyses data within seconds or minutes of it being generated.
term
Referral traffic
Referral traffic is traffic that arrives from a link on another website rather than from a search engine…
term
Reporting identity
Reporting identity is the setting that decides how GA4 recognises users across sessions and devices in reports.
term
Reranking
Reranking reorders retrieved results with a more precise model, so the best passages go to the language model…
term
Retention rate
Retention rate is the percentage of users who come back or stay active over a given period.
term
Retrieval-augmented generation (RAG)
RAG is a technique that retrieves relevant information from your own sources and gives it to a language…
term
Return on ad spend (ROAS)
Return on ad spend is the revenue generated for every unit of currency spent on advertising.
term
Reverse ETL
Reverse ETL sends modelled data from the warehouse back into operational tools such as CRMs and ad platforms.
term
Role-based access control (RBAC)
RBAC gives people access to data and tools based on their role, rather than granting permissions one by…
term
Row-level security
Row-level security restricts which rows of a table a user can see, based on who they are.
S
tool
Salesforce
Salesforce is a widely used customer relationship management platform.
term
Sample ratio mismatch (SRM)
A sample ratio mismatch is when the actual split of users between variants differs from the intended split.
term
Schema
A schema defines the structure of data: the tables, columns and data types it contains.
term
Scorecard
A scorecard is a compact view of a handful of KPIs against targets, often with status indicators.
term
Scroll depth
Scroll depth measures how far down a page visitors scroll, often reported in percentages.
tool
Segment
Segment is a customer data platform that collects events once and sends them to many tools.
term
Self-service BI
Self-service BI lets business users explore data and build reports themselves, without waiting for analysts.
term
Semantic layer
A semantic layer defines your business metrics and dimensions once, so every tool and person gets the same…
term
Semantic search
Semantic search finds results by meaning rather than exact keywords.
term
Semi-structured data
Semi-structured data has a flexible shape, like JSON, rather than fixed rows and columns.
term
Sequential testing
Sequential testing uses statistical methods that remain valid when you check results repeatedly while a test runs.
term
Server-side tagging
Server-side tagging sends data from the browser to a server you control, which then forwards it to analytics…
term
Server-side testing
Server-side testing runs experiments in your backend, so users get the assigned variant before the page is rendered.
term
Session
A session is a group of user interactions on your site or app within a given time frame.
term
Session recording
Session recording captures a replay of how an individual visitor interacts with your site, including clicks, scrolls and…
term
Simpson's paradox
Simpson's paradox is when a trend that appears in several groups reverses when the groups are combined.
term
Single sign-on (SSO)
Single sign-on lets users access many tools with one login managed by a company identity provider.
term
Site search tracking
Site search tracking records what visitors type into your internal search, revealing what they cannot find.
term
Slowly changing dimension (SCD)
A slowly changing dimension is a descriptive attribute, like a customer segment, whose value changes over time and…
tool
Snowflake
Snowflake is a cloud data platform used as a data warehouse, with storage and compute scaled separately.
term
SQL
SQL is the standard language for querying and managing data in relational databases and warehouses.
tool
SQLMesh
SQLMesh is a data transformation framework with virtual environments and strong change management.
term
Staging layer
The staging layer holds lightly cleaned copies of source tables, one per source table, as the base for…
term
Star schema
A star schema organises data into a central fact table surrounded by descriptive dimension tables.
term
Statistical power
Statistical power is the probability that a test detects a real effect of a given size.
term
Statistical significance
A result is statistically significant when it is unlikely to be explained by chance alone, given a chosen…
term
Statistics
Statistics is the science of collecting, analysing and interpreting data, and quantifying uncertainty.
tool
Statsig
Statsig is a product experimentation platform with feature gates, experiments and analytics.
term
Surrogate key
A surrogate key is a generated identifier, with no business meaning, used to uniquely identify a row in…
term
Synthetic data
Synthetic data is artificially generated data that mimics the properties of real data.
term
System prompt
A system prompt is the standing set of instructions that defines how an AI assistant behaves in an…
T
tool
Tableau
Tableau is a visual analytics platform known for flexible, interactive visualisations.
term
Tag manager
A tag manager is a tool for deploying and managing tracking code on a website without changing the…
tool
Terraform
Terraform is an infrastructure-as-code tool for defining and managing cloud resources in files.
term
Text-to-SQL
Text-to-SQL is using AI to turn a plain-language question into a SQL query.
term
Third-party cookies
Third-party cookies are set by a domain other than the one you are visiting, mainly for advertising and…
term
Token
A token is a small piece of text, often part of a word, that language models read and…
term
Tracking pixel
A tracking pixel is a tiny, usually invisible image or script that records an interaction, such as an…
term
Type I and type II errors
A type I error is a false positive, declaring an effect that is not real; a type II…
U
term
User ID
A user ID is a unique identifier you assign to a logged-in user so analytics can recognise them…
term
User property
A user property describes an attribute of a user that stays the same across events, such as plan…
term
UTM parameters
UTM parameters are tags added to a URL so analytics tools know which campaign, source and medium sent…
V
term
Vanity metric
A vanity metric looks impressive but does not help you make decisions, such as total page views or…
term
Variance reduction
Variance reduction techniques make experiments more sensitive, so they reach conclusions with less data.
term
Vector database
A vector database stores embeddings and quickly finds the ones most similar to a query.
term
View-through conversion
A view-through conversion is a conversion that happens after someone saw an ad but did not click it.
tool
VWO
VWO is an A/B testing and conversion optimisation platform with visual editing, heatmaps and surveys.
Tell us what you need. We'll scope it.
Pricing is tailored to your sources, volume and the parts of the platform you use. Request a demo or book a call with the team.