Systematic examination, interpretation, and transformation of raw data into meaningful insights, patterns, and trends. Part of
monitoring
and other crucial business processes. It involves the application of various statistical, mathematical, or other expert methods to uncover relationships, draw inferences, and derive valuable information from datasets. Unlike data collection, which focuses on the gathering of information, data analysis centers on exploring, organizing, and interpreting data to reveal underlying patterns or relationships that can inform decision-making and support the achievement of specific objectives.
Close terminology
Examples of synonimes and close terminology:
Data Exploration
The preliminary phase of data analysis involving the examination and summary of key characteristics of the dataset.
Inferential Statistics
Statistical techniques that make predictions or inferences about a population based on a sample of data.
Hypothesis Testing
The process of assessing the validity of a claim or hypothesis about a population parameter using statistical methods.
Data Visualization
The representation of data through charts, graphs, or other visual elements to facilitate understanding and insights.
Outlier Detection
Identifying data points that deviate significantly from the overall pattern in a dataset.
Predictive Modeling
Building models to predict future outcomes or trends based on historical data.
Cross-Validation
A technique used to assess the performance of a predictive model by partitioning the data into subsets for training and testing.
Requirement
Questions or objectives that guide the analysis and help determine the appropriate approach, methods and indicators. The questions ensure that the analysis is aligned with the goals of the analysis.
The data analysis needs requirements as the process input, e.g. from
goal-setting
, or ad hoc
decision
. It can also form requirements as an output for other processes, like:
planning
,
decision
or
change management
.
Problem Formulation
Crucial process of devising a data science solution to a business problem. Its purpose can be
identification
of crucial elements, opportunities and risks,
prediction
,
optimization
of processes etc.
Modelling
Creating a simplified representation of a complex system or dataset to understand its structure and handle its crucial elements.
Extrapolation
Extrapolation is a analytical technique, used broadly across various knowledge domains, incl. data science, to use information that is already known to estimate values, beyond the original observation range.
Hypothesis
Specific statement or assumption that is tested during the analysis. Hypotheses provide a framework for focused analysis, easier calibration and interpretation of results. At the same time it is connected with risk of research bias.
Likelihood
Probability of an event occurring, influencing risk assessment, decision-making, and strategy. Companies use data, market trends, and scenario planning to estimate the chances of success, failure, or disruptions. For example, a retailer may analyze past sales data to predict the likelihood of increased demand during the holiday season. Investors assess the likelihood of returns before funding startups, while businesses evaluate potential risks like cybersecurity threats or supply chain issues. Understanding likelihood helps organizations prepare, mitigate risks, and make informed decisions for growth and stability.
Impact level
Degree of effect an event, risk, or decision has on operations, financial performance, reputation, or strategy. It is often assessed alongside likelihood to prioritize risks and opportunities. with impact measuring the severity of the consequences if the event occur
Application
Analytical studies are not always used, even if their methodology and conduct were appropriate, as well as their results significant for the activity analyzed.