Data Audit Report Buhi Supply Cob Y D U R C H D E N W A L D

Data Audit Report Buhi Supply Cob Y D U R C H D E N W A L D G Lo

Data-Audit Report: Buhi Supply Co. B Y D U R C H D E N W A L D G LO B A L This report outlines the findings by Durchdenwald Global (DG) from a database audit for Buhi Supply Co. In this audit, DG assessed the integrity and usability of Buhi’s data without making any changes or corrections to it. Trustworthy data is a critical element in making data-driven business decisions with confidence. Therefore, we recommend that Buhi address errors and issues in its data to the fullest extent possible.

Paper For Above instruction

The effectiveness of data management is fundamental to the success of any data-driven organization. This report evaluates the integrity and quality of the Buhi Supply Co. database, systematically identifying issues such as missing values, outliers, impossible entries, inconsistent data, erroneous formatting, duplicate records, and potential structural inconsistencies. These issues can significantly impair decision-making, operational efficiency, and strategic planning if not addressed appropriately.

Assessment of Data Quality and Integrity

Our audit identified several critical issues across multiple data dimensions. Each type of data irregularity presents specific challenges but collectively underscores the importance of rigorous data governance. Addressing these issues is essential to enhance the reliability and usability of Buhi’s data assets.

Missing Values

Missing data points, known as null or blank entries, can impact analyses and reporting by introducing bias or inaccuracies. In Buhi’s database, a total of 126,061 missing values were detected. For example, the image_type field in the campaigns table contains 80 missing entries, which may not be critical if the field is optional. Similarly, in the employee_surveys table, missing responses in fields like job_satisfaction and mgr_relationship could be acceptable if the survey design allows for optional responses.

It is recommended that Buhi review each missing value systematically, determining whether its absence could influence business decisions or analytics. Where missing data is significant, strategies such as record deletion or data imputation based on existing values should be implemented.

Outliers

Outliers are data points that significantly deviate from other observations and may distort analytical results. The audit uncovered 3,754 instances of outliers, such as order revenue values exceeding $150,000 when typical values range from $35 to $4,500. Similarly, impression counts in advertising campaigns often range from zero to 1,600, with outliers reaching into the millions.

Buhi should evaluate the impact of these outliers on its data analyses. For critical insights, filtering outliers during queries or removing such records may be necessary to ensure accurate reporting and decision-making.

Impossible Values

Impossible values violate logical or domain-specific constraints, rendering them unequivocally incorrect. Our analysis found 1,548 such values, including feature_score entries outside of the 1-5 scale and negative age entries, with some ages recorded as high as 128 years. These errors likely originate from data entry mistakes or system glitches.

Buhi’s approach should be to remove these impossible values from the datasets and treat them as missing data to prevent skewing results. Ongoing validation rules and input constraints can prevent recurrence.

Inconsistent Values

Data inconsistencies occur when related data does not align logically, raising concerns about correctness. The audit identified 41,222 such instances, including exceptionally high bag_count entries (>100) and role descriptions like "software engineer" with unexpectedly low wages.

Inconsistencies warrant further investigation. When corroborated with other data points, flags can be removed; otherwise, the records should be corrected or omitted to uphold data quality standards.

Erroneous Formatting

Errors in data formatting impede analysis and may result from manual entry or software issues. The audit revealed 4,261 such instances, including spelled-out quantities like "six" instead of "6" and expense amounts written in words like "eighty-seven dollars." These formats need to be standardized.

Buhi should implement data cleansing procedures to convert textual numbers into numeric formats, and remove or correct ambiguous entries that defy precise transformation.

Duplicate Records

Duplicate records can distort metrics, lead to double-counting, and impact operational decisions. Through checking for identical fields, 27,049 potential duplicates were found. Examples include multiple delivery records with identical delivery_id, which should be unique, and repeated survey entries.

It is advisable to review suspected duplicates thoroughly. Confirmed duplicates should be consolidated or deleted, leaving a single source of truth in the database.

Discussion of Data Issues within Organizational Context

The identified data irregularities reflect underlying data entry processes, validation protocols, and system controls. For example, missing values and formatting errors suggest inadequate data validation rules during data entry. Outliers and impossible values may indicate errors rather than genuine data. Inconsistent data could result from inconsistent standards or manual updates.

Addressing these issues requires a multi-faceted approach, including implementing stricter data validation rules at the point of entry, automating error detection, and training staff in data quality best practices. Additionally, repeated data audits are critical to maintaining high standards over time.

Implications for Business Decision-Making

High data quality is essential for accurate reporting, predictive modeling, and strategic planning. The presence of missing data can lead to biased analyses; outliers may skew the results, and impossible or inconsistent values can distort understanding of customer behavior, operational efficiency, or financial performance. Duplicated records further compound these problems by inflating metrics and causing double counting.

Implementing robust data governance strategies can mitigate these risks, leading to more reliable insights and better decision-making, ultimately improving organizational performance and competitive advantage.

Recommendations and Next Steps

1. Systematically review missing values and address significant gaps through data imputation or record deletion.
2. Identify and filter out or correct outliers to prevent skewed analysis results.
3. Remove impossible values and reinforce data input validation constraints.
4. Investigate and resolve inconsistent data entries with corroborating data sources.
5. Standardize formatting across datasets, converting textual data into proper numerical formats where applicable.
6. Conduct detailed review of suspected duplicate records, consolidating or removing as appropriate.
7. Implement ongoing data validation, automated error detection, and staff training to sustain data quality improvements.

Through these steps, Buhi Supply Co. can significantly enhance its data reliability, supporting better operational, analytical, and strategic outcomes.

References

• Kimball, R., & Ross, M. (2013). The Data Warehouse Toolkit: The Definitive Guide to Dimensional Modeling. John Wiley & Sons.
• Inmon, W. H. (2005). Building the Data Warehouse. Wiley.
• Redman, T. C. (2018). Data Driven: Creating a Data Culture. Harvard Business Review Press.
• Wang, R. Y., & Strong, D. M. (1996). Beyond Accuracy: What Data Quality Means to Data Consumers. Journal of Management Information Systems, 12(4), 5-33.
• Batini, C., & Scannapieco, M. (2006). Data Quality: Concepts, Methodologies, and Techniques. Springer.
• Data Management Body of Knowledge (DMBOK). (2017). Data Management Association.
• García-Magro, J. L., et al. (2018). Data Cleaning Techniques for Big Data. IEEE Transactions on Big Data, 4(4), 540-554.
• Olson, J. E. (2010). Data Quality: The Field Guide. Morgan Kaufmann.
• Patrício, M., et al. (2019). Data Governance: Principles and Practices. Springer.
• Berti, S., & Minelli, M. (2019). Towards a Data Quality Framework for Data Governance. IEEE International Conference on Big Data, 591-595.