Glossary

A/B Testing is a method of comparing two versions of content—such as web pages or emails—by showing each to different user segments and measuring performance. It helps identify which version drives better engagement or conversion rates.

Anomaly detection identifies data points or trends that differ significantly from the norm. This is useful for catching fraud, performance dips, or system errors early by highlighting unusual spikes, drops, or deviations in datasets.

APIs are sets of rules that allow different software systems to communicate and exchange data. In analytics, APIs pull data from platforms like CRMs, ad tools, or databases into dashboards or data warehouses.

AI refers to computer systems that simulate human intelligence. In analytics, it powers automation, pattern recognition, natural language processing, and predictive modeling, helping uncover insights faster and more efficiently.

An attribution model assigns credit to marketing touchpoints in a customer journey. It helps analyze how different channels—email, search, social—contribute to conversions, informing budget allocation and ROI measurement.

Augmented analytics uses AI and machine learning to automate parts of the analytics process, including data prep and insight discovery. It reduces manual effort and enables non-technical users to uncover insights faster.

Batch processing handles large volumes of data at once, typically on a schedule (e.g., nightly). It’s ideal for updating reports, syncing systems, or running periodic data transformations that don’t require real-time updates.

Big Data refers to massive datasets that are too large or complex for traditional tools to handle. It includes structured and unstructured data and requires specialized technologies like Hadoop, Spark, or cloud warehouses.

Bounce rate measures the percentage of users who visit a page and leave without taking further action. A high bounce rate may indicate poor user experience, slow load times, or irrelevant content needing optimization.

Business analytics involves analyzing past and present data to guide strategic decisions. It blends data mining, statistical analysis, and forecasting to uncover patterns, risks, and opportunities across business functions.

BI encompasses the tools and processes for collecting, analyzing, and visualizing business data. It turns raw data into actionable insights via dashboards, reports, and visualizations to support decision-making.

Churn rate is the percentage of customers who stop using a product or service over a period. It helps companies understand retention trends and assess the effectiveness of customer success or loyalty strategies.

Cloud computing delivers services like data storage, processing power, and software applications over the internet. It’s scalable, cost-effective, and commonly used for hosting analytics tools and data warehouses.

Cohort analysis groups users based on shared characteristics or start times (e.g., signup month) to study their behavior over time. It helps track retention, engagement, or revenue trends across different user segments.

Conversion rate is the percentage of users who complete a desired action—like purchases or sign-ups—out of the total visitors. It’s a key metric for marketing and UX performance across campaigns or landing pages.

Correlation measures how two variables move in relation to each other. A positive correlation means both rise together; a negative one means one falls as the other rises. It doesn’t imply causation but can hint at trends.

CRM refers to software that manages customer interactions and data. It stores contact details, purchase history, and support tickets, enabling sales, service, and marketing teams to personalize outreach and track relationships.

CAC calculates the cost to acquire a new customer by dividing total marketing and sales spend by the number of new customers gained. It helps assess the efficiency and scalability of customer acquisition strategies.

CLV estimates the total revenue a customer brings to a business over their lifetime. It helps brands segment high-value users, guide retention efforts, and determine how much to invest in acquiring or supporting each customer.

A dashboard is a visual interface that displays key metrics, KPIs, and data visualizations in one place. It offers real-time or periodic updates and is used to monitor performance, trends, and goals across business areas.

Data analytics involves collecting, transforming, and interpreting data to uncover insights, trends, or patterns. It powers smarter decisions across areas like marketing, operations, finance, and customer experience.

Data architecture defines how data is collected, stored, and managed across systems. It includes structure, integration, and flow of data, enabling reliable analytics and supporting scalability as business data grows.

A data catalog is a searchable inventory of an organization’s data assets. It contains metadata—like descriptions, source, and owner—so users can easily find, understand, and use trusted datasets across teams.

Data cleansing involves fixing errors, inconsistencies, or duplicates in data. It ensures accuracy, completeness, and quality—critical for generating reliable insights from analytics, reporting, and dashboards.

Data democratization makes data accessible across an organization, not just to analysts. It empowers non-technical users with tools and governance to explore insights while ensuring data consistency and control.

A reference that defines database elements like fields, tables, and data types. It ensures consistent understanding of data across teams—e.g., “Cust_ID” = unique customer ID.

Building and managing systems that collect, clean, and prepare data for analysis. Think: automating pipelines that pull in data and feed it into dashboards.

A smart layer that connects all of a company’s data—across cloud, on-prem, and streams—using AI and metadata to simplify access, integration, and management.

Rules and roles that ensure data is accurate, secure, and well-managed. It defines who owns data, how it’s handled, and ensures compliance and trust.

Combining data from multiple sources into one view—like merging CRM, finance, and web analytics data to track a customer journey in one dashboard.

A central storage for raw data of all types and formats. It stores everything as-is, making it flexible for big data, advanced analysis, or future use.

Blends the scalability of a data lake with the structure of a warehouse. Ideal for storing raw data while still enabling reliable analysis via SQL and BI tools.

A smaller, focused version of a data warehouse built for a specific team—like a marketing data mart with campaign and lead data only.

A decentralized setup where teams own their data as products. Each domain (like sales or marketing) manages its own datasets for easier use and access.

Using algorithms to explore large datasets and find hidden patterns or insights—like discovering buying habits or detecting fraud.

Designing how data is structured in a system—like diagrams of tables and relationships to ensure it supports reporting and analysis needs.

Upgrading from old systems to modern, cloud-based data platforms that are faster, scalable, and analytics-ready—like moving from spreadsheets to BigQuery.

Measures how accurate, complete, and usable data is. Good data quality means reliable insights; poor quality leads to bad decisions.

The use of statistics, code, and domain expertise to analyze complex data and build models that predict trends or uncover insights.

When data is stuck in one team or tool and not shared across the company. Silos lead to gaps in insight and poor collaboration.

Explaining insights through visuals and narrative—so instead of just showing numbers, you show what they mean and why they matter.

A plan for how a business collects, manages, and uses data to meet goals. It aligns tools, people, and processes to turn data into value.

Turning data into charts, maps, or dashboards so it’s easy to understand. Helps teams spot patterns, trends, and outliers quickly.

A centralized system that stores cleaned, structured data for analysis. It’s designed for fast queries and consistent reporting across teams.

Making business decisions based on data analysis, not gut feeling. It helps teams use facts (like ROI data) to guide actions. SR Analytics builds tools that support this approach.

A type of AI that uses layered neural networks to recognize patterns—great for tasks like image recognition or text generation.

Looks at historical data to answer “What happened?”—using reports and dashboards to summarize trends and performance.

Digs into data to find out “Why did it happen?”—using filtering and analysis to uncover the causes behind patterns or changes.

A feature in dashboards that lets users click into a summary (like total sales) to view more detailed breakdowns (like sales by product).

Tracks and analyzes online store data—like page views, cart abandonment, and conversion rates—to improve the customer journey and boost sales.

A data workflow where raw data is extracted, loaded into storage (like a data lake), then transformed inside the system. Fast, flexible, and great for big data.

Analytics like charts or dashboards built into everyday tools (like CRMs or apps), so users get insights right where they work—no need to switch tools.

A classic data process: pull data from sources, clean/reshape it, and load it into a database. Ideal for making raw data useful and ready for analysis.

Captures specific user actions on sites or apps—like button clicks or video plays—so you can see what users do, not just what pages they visit.

The first step in analyzing data—using visuals and stats to explore patterns, spot issues, and shape what comes next in the analysis process.

Data collected directly from your audience (like website or purchase behavior). It’s accurate, privacy-safe, and ideal for personalized marketing.

Using past data to predict future trends—like monthly sales or user growth. Helps with planning, budgeting, and making informed business moves.

Looks at each step in a process (like a checkout flow) to see where users drop off. Helps fix leaks and boost conversions across the customer journey.

EU law that gives people control over their personal data. Businesses must follow strict rules—like getting consent and allowing deletion requests.

AI that creates new content—text, images, or data—based on what it learned. Think tools like ChatGPT or AI that writes product descriptions or simulates trends.

A tool that shows how users interact with your site or app—tracking traffic, behavior, and conversions to help you improve performance and UX.

An open-source system for storing and processing huge datasets across many machines. Used for big data crunching, especially before newer tools like Spark took over.

A statistical method to test if a result is meaningful or just chance. Used in A/B tests to see if changes (like a new site design) actually improve outcomes.

A meaningful discovery from data that leads to action—like finding out a certain customer group drives repeat sales. It’s more than just numbers; it informs decisions.

A key metric that shows if you’re hitting your business goals—like conversion rate, revenue, or churn. KPIs track what matters most to your success.

A type of AI where systems learn from data to make predictions—like spotting fraud or forecasting churn—without being explicitly programmed.

The analysis of marketing performance data to boost ROI. Tracks things like conversions, campaign success, and user behavior to guide smarter marketing.

Uses stats to show how different marketing channels impact sales. Helps decide where to spend—like proving TV ads work better than print for one product.

Data about data. It gives context—like who created a file, what fields a table has, or how a metric is defined—so you understand and trust what you’re working with.

Tools and practices for deploying and managing machine learning models in the real world. Automates updates, monitors performance, and ensures models stay reliable.

AI that helps computers understand human language. Powers chatbots, sentiment analysis, and tools that summarize or interpret text data.

A type of flexible database that handles unstructured or fast-moving data—like documents, key-values, or graphs. Great for scale and variety.

Lets users quickly explore data across dimensions (like product, time, region) via cubes or dashboards. Built for fast, interactive analysis.

Handles real-time transactional data—like online orders or bank records. It’s built for quick inserts and updates, not heavy analysis.

A data point that’s way off compared to others—like a $500K sale when all others are under $50K. Might signal an error, anomaly, or something worth digging into.

Any data that can identify a person—like name, email, or ID numbers. PII must be handled carefully to meet privacy laws like GDPR, often using encryption or anonymization.

A Microsoft platform for building interactive dashboards and reports. It connects to many data sources and helps users turn raw data into clear, shareable insights.

Uses historical data and algorithms to forecast future outcomes—like churn, demand, or sales—so businesses can act early, not just react after the fact.

Recommends actions based on predictive insights. For example: not just forecasting low stock, but suggesting when and how much to reorder to avoid shortages.

Non-numerical data like text, labels, or categories—e.g., customer feedback or interview responses. It adds context and depth to quantitative findings.

Numerical data that can be measured—like sales, visits, or ratings. It powers charts, averages, and KPIs, helping businesses track performance at scale.

Analyzing data as it’s created—like tracking live website traffic or sales. Helps teams react instantly to trends or issues instead of waiting for reports.

A statistical method for understanding how one variable affects another—like how marketing spend impacts sales. Often used in forecasting and diagnostics.

Organizing data into summaries—charts, tables, or PDFs—to share updates on performance. Reporting shows “what happened” and is often automated for consistency.

A metric showing how much revenue is earned per dollar spent on ads. For example, $5K in sales from $1K in ads = 5:1 ROAS. Higher is better.

Shows how profitable an investment is. It’s the net gain compared to the cost—e.g., a $50K return on a $100K spend = 50% ROI. Helps guide smart budgeting.

A method for finding the true reason behind a problem—not just the surface issue. Helps teams fix issues at the source instead of patching symptoms.

Another company’s first-party data shared with you via a partnership. It’s usually high-quality and can help enrich your own insights—like co-branded marketing.

Dividing a group (like customers) into smaller segments based on traits or behavior—e.g., frequent vs. one-time buyers—so strategies can be more targeted and effective.

Lets non-technical users explore data and build reports on their own—no waiting on IT. Tools like Power BI and Tableau make it easy to answer questions and uncover insights independently.

A language used to query and manage data in relational databases. With SQL, you can select, filter, join, and analyze data—foundational for reporting and BI work.

Data organized in tables with rows and columns—like spreadsheets or databases. Easy to search and analyze. Think: sales records, customer lists, or sensor logs.

A type of machine learning that learns from labeled data (where inputs have known outputs). Used to predict outcomes—like churn, credit risk, or sales.

A top-tier data visualization tool that helps users turn data into interactive, shareable dashboards—no coding needed. Great for exploring and presenting insights visually.

Data bought or licensed from external aggregators who didn’t collect it directly from your customers. Used to enrich targeting but now faces privacy and accuracy concerns.

Data without a clear format—like text, images, or audio. It’s messy but rich in insights, often analyzed with AI tools like NLP or computer vision.

Machine learning that finds hidden patterns in unlabeled data—like customer segments or product groupings—without being told what to look for.

Tracks how people use your website—measuring visits, clicks, conversions, and more. Helps spot what’s working and what needs fixing online.

Compares a metric to the same time period in the previous year—like “January sales up 10% YoY.” Helps track growth trends while accounting for seasonality.

Data customers give you directly—like survey responses or preference settings. It’s accurate, privacy-safe, and great for personalization.