Validating data involves assessing that the planned data sources can and should be used and, when accessed, the data obtained are providing the types of results expected. Since a detailed analysis of the data is yet to be performed, the objective of validation at this point is high-level.

Business validation involves having the business stakeholders approve the data sources and establish the acceptance criteria that define the parameters for assessing the accuracy of the data. It also includes validating any relevant requirements. For example, if the outcome of data analysis is expected to be a report, business validation involves validating the format and data elements to be included in the report. Technical validation involves technical testing and validation to assess data quality. There are several characteristics reflected in high-quality data, such as:

• Accuracy: the data is correct and represents what was intended by the source. Accurate data is not misleading. Accuracy might be assessed by comparing numbers displayed by a front-end system with data retrieved from the database.
• Completeness: the data is comprehensive and includes what is expected and nothing is missing. Completeness might be assessed by ensuring required fields do not include null values.
• Consistency: how reliable the data is. Data values are consistent when the value of a data element is the same across sources. Consistency might be assessed by ensuring only date values are being displayed in date fields.
• Uniqueness: data that is unique is valuable to an organization. Uniqueness might be assessed by determining whether any duplicates exist in the data.
• Timeliness: data that is fresh and current is more valuable than data that is out of date. Timeliness might be assessed by determining whether the data being received is for the period being requested.

Data validation may be performed by a data analyst, data scientist, or business analysis practitioner with sufficient skills to use the necessary tools to access data and the underlying competencies to analyze the results. Business validation is performed by key stakeholders with the authority to approve data sources for use in analytics initiatives and the knowledge to assess data accuracy in collaboration with the analysts.

When validating data, analysts use techniques such as data mapping and business rules analysis. Data mapping is used to create a source-to-target data map to define the mapping between the data sources being used and the target system. Business rules analysis provides an understanding of the business rules governing the data by providing guidance as to what should be validated. Conceptual thinking skills help make sense out of the large sets of disparate data sources under analysis and to draw relationships and understanding from the data. Business knowledge provides context to the data being validated, helping analysts determine if the data is accurate and complete.