Data-Driven Fraud Assignment
LaKaden Brown
Liberty University
ACCT:406
Prof: Anan Sturgess
February 1, 2024
2
Data-Driven Fraud Assignment
Fraud detection methods using financial statements involve the analysis of financial data
to identify irregularities, inconsistencies, or patterns indicative of fraudulent activities. To
understand more on the topic, we need to explain what Data-Driven Fraud is. In our textbook, it
shows the definition of it. “Data-driven fraud detection is using data, usually through the mining
of those data, to identify patterns, anomolies, etc. to find possible fraud symptoms.” (Albrecht,
Albrecht, Albrecht, & Zimbelman, 2019, Chapter 6 Introduction). So, this shows it uses data to
find patterns to find possible symptoms of Fraud. More information on financial statements is in
the textbook. “Data-driven analysis at the highly summarized financial statement level is also
useful and important, especially in external audits. This section presents a specialized type of
data-driven analysis that targets fraud in financial statements.” (Albrecht, Albrecht, Albrecht, &
Zimbelman, 2019, Section 6-9). To sum this all up this whole section would explain financial
statements in data-driven analysis. It shows the type of data that targets the fraud to happen. This
is important when trying to detect fraud and prevent fraud from happening. Three cases that I
will be mentioning are Nantucket, Benford’s Law, and Kelly Enterprises. Along with 2 methods
for each that explain each case. All tables are provided at the end of the assignment.
Nantucket
After years of steady expansion, Nantucket-based Bucket Corp., a manufacturer of wood
furniture, is seeing a drop in revenues. The procurement division's controls are found to be
leaking, similar to holes in a bucket, according to the company's financial study. This control
leakage raises the possibility of ineffectiveness, poor administration, or even fraud in the
procurement process. Furthermore, problems have been felt in the relationships between
suppliers and purchasers, suggesting possible problems in the supply chain. It is critical to
3
investigate the underlying issues in the procurement division as there is a suspicion that these
difficulties are related to the fall in profitability. “By distinguishing behaviors (suspicious and
non-suspicious), it is possible to discover transactions that are part of a pattern that is not yet
known and that would have been left undiscovered if only traditional means were used.”
(Sánchez-Aguayo, M., Urquiza-Aguiar, L., & Estrada-Jiménez, J., 2022). I feel like this is
important to know when talking about the methods of fraud. It gives more of an insight into the
topic at hand. Showing how behaviors are a way to discover transaction patterns that are not
known. Two fraud methods fit with this case. Cost-benefit analysis, supplier relationship
management. There are steps to each of these methods that would need to take place to get an
understanding. First is cost-benefit analysis. The 1st step is to select relevant ratios: choose key
ratios based on the aspects you want to assess, such as liquidity, profitability, solvency, and
efficiency. The 2nd step is to gather data: collect the necessary financial information from the
company's statements. The 3rd step is to calculate ratios: Use the formulas to compute ratios.
Some examples: Current Ratio = Current Assets / Current Liabilities and Net Profit Margin =
(Net Profit / Revenue) * 100. These are some examples of ratios that would be used to help with
data. The 4th step is to compare to benchmarks: compare calculated ratios to industry
benchmarks or historical data to assess performance. The final step is to interpret results: analyze
the ratios and interpret their implications for the company's financial health. The results of the
analysis. The analysis revealed that raw material costs, transportation, and storage were the
major cost drivers in the procurement process. Total procurement costs were calculated,
highlighting areas where expenditure was higher than anticipated. Benefits such as material
quality, timely deliveries, and supplier relationships were assessed, with a focus on their impact
on overall operational efficiency. The return on investment indicated that the current
4
procurement process was not generating optimal value. Recommend implementing changes to
reduce costs, negotiate better terms with suppliers, and enhance the overall efficiency of the
procurement process. This would show the results of using this analysis. The next analysis is
Supplier Relationship Management (SRM). The 1st step is to assess supplier performance:
evaluate the performance of current suppliers in terms of quality, reliability, and cost-
effectiveness. The 2nd step is to identify key suppliers: identify suppliers critical to the
procurement process and overall business operations. The 3rd step is to negotiate contracts: revisit
existing contracts and negotiate terms with key suppliers to achieve better pricing, favorable
payment terms, and improved overall value. The 4th Step is to diversify the supplier base:
consider diversifying the supplier base to mitigate risks associated with dependence on a single
supplier. The final step is to implement SRM strategies: develop and implement strategies to
build strong, collaborative relationships with key suppliers, fostering mutual success. This shows
the steps of this method. Now let's investigate the results based on the information. Supplier
evaluations indicated inconsistencies in terms of reliability, quality, and cost-effectiveness. Key
suppliers critical to operations were identified, emphasizing the need for strengthened
relationships. Contract renegotiations with key suppliers were recommended to improve terms
and achieve better overall value. A strategy to diversify the supplier base was proposed to
mitigate risks associated with dependency on a single supplier. Recommendations include the
implementation of SRM strategies to build collaborative relationships and ensure mutual success.
This would include some results based on this method that was given.
5
Benford’s Law
The Article, “Benford’s Law and COVID-19 Reporting”, by Koch C, and Okamura K., shows
what Benford's law is and what it talks about in real-time. “Benford’s Law is used to detect fraud
or flaws in data collection based on the distribution of the first digits of observed data. A Benford
distribution of first digits arises naturally for exponential processes with multiple changes of
magnitude, Michalski and Stoltz (2013).” (Koch C., Okamura K, 2020). This would show what
Benford law is and give us a good definition of it. Two methods include Benford’s Law and
Anomaly. The 1st step is to understand Benford's Law. The objective of this step is to familiarize
yourself with the principles of Benford's Law. The 2nd step is to extract the leading digits. The
objective of this step is to isolate the leading digits from the amounts in the financial data. The 3rd
step is to create frequency distribution. The objective of this step is to count the occurrence of
each leading digit. The 4th step is to compare with Benford's Law. The objective of this step is to
assess whether the leading digit distribution aligns with Benford's Law. The 5th step is to identify
deviations. The objective of this step is to flag potential anomalies or deviations from Benford's
Law. The 6th step is to investigate Deviations. The objective of this step is to understand the
reasons behind deviations. The final step is continuous monitoring. The objective of this step is
to implement ongoing monitoring for leading digit distributions. Now the investigation results
that come with this method. Leading Digit 1 (Observed: 28.5% vs. Expected: 30.1%): Slight
deviation but within an acceptable range. Could be influenced by various factors such as
transaction types or business practices. Leading Digit 2 (Observed: 19.2% vs. Expected: 17.6%):
Slight deviation, but not alarming. Similar to leading digit 1, variations may occur naturally.
Leading Digits 3 to 9: The observed frequencies for leading digits 3 to 9 generally follow
Benford's Law expectations with slight variations. No significant anomalies are apparent. This
6
shows the results using Benford’s law and the leading digit. Recommendations based on the data
provided. Implement continuous monitoring systems for leading digit distributions to detect any
future anomalies promptly. Conduct periodic reviews of financial data to identify anomalies or
changes in patterns. Strengthen internal controls and conduct a more in-depth investigation if
future analyses reveal consistent deviations. The steps for Anomaly. The 1st step is to define
normal behavior. Establish a baseline using historical data representing normal patterns. The 2nd
step is to select features for analysis. Choose relevant features or variables for anomaly detection.
The 3rd step is to choose an anomaly detection technique. Select an appropriate method
(statistical models, machine learning algorithms) based on data characteristics. 4th step is to train
the anomaly detection model. Train the chosen model using the normal data to identify typical
patterns. The last step is to apply the model to new data. Use the trained model to detect
anomalies in real-time or recent data, applying a defined threshold. Investigation results using
this method. Transactions were flagged as potential anomalies based on deviation from the
established threshold. Conducted a brief investigation into each flagged anomaly, considering
supporting documentation and context. Determined the nature of each anomaly, categorizing
them as either legitimate changes or potential irregularities. Detected anomaly based on results.
The 1st one is Transaction 3 (2003): Sharky’s Used Car Dealership for Yugo truck. Amount:
$4,987.36. Reason for anomaly: unusually high transaction amount compared to historical data.
The 2nd one is Transaction 6 (2006): Grainger Corp. for power tools. Amount: $254.14 Reason
for anomaly: relatively low transaction amount compared to historical data. The 3rd one is
Transaction 10 (2010): Bank of America for loan payment. Amount: $477.67. Reason for
Anomaly: slightly higher transaction amount compared to historical data. Recommendations for
this follow. Further, refine anomaly detection methods using advanced statistical techniques or
7
machine learning algorithms. Implement continuous monitoring systems for real-time anomaly
detection. Conduct periodic reviews of financial data to update anomaly detection models.
Kelly Enterprises
According to Kelly Enterprises, Inc.'s Statement of Cash Flows, net income increased
from $450 million to $900 million between 2016 and 2018, indicating a good trend. Positive
cash flow from operating operations is a result of adjustments to inventories, accounts payable,
and receivable. Financing activities imply growing long-term debt and cash dividends, whilst
investing activities suggest significant capital expenditures. Notwithstanding favorable elements,
the business had a significant $316 million decline in cash in 2018, which prompted more
research into possible effects on the company's financial health and strategic decision-making. I
feel like when talking about this you need to know some background. “The statement of cash
flows is an analytical statement of the movement of cash changes that took place in the entity,
whether increasing or decreasing, and that identifies the reasons for these changes, meaning that
it is a depiction of the sum cash transactions (Bala, 2017)”. TAMIMI, O., & ORBÁN, I. (2022.
This shows what the point of a statement of cash flow is and it helps describe this case as well.
The two Methods are Cash flow Analysis and Ratio Analysis. The steps to a cash flow analysis.
The 1st step is net income assessment. Start by scrutinizing the net income over the specified
period. Understand the relationship between reported profits and actual cash movements.2nd step
is operating cash flow components. Break down the operating cash flow section, focusing on
changes in accounts receivable, accounts payable, and inventory. Investigate significant
fluctuations and assess their reasonableness. The 3rd step is investing and financing activities.
Analyze the investing and financing activities to identify any unusual patterns. 4th step is cash
8
position change. Scrutinize the overall change in cash. When instigating you can find red flags in
each step. The analysis reveals a substantial increase in net income from $450 million in 2016 to
$900 million in 2018. While this might initially seem positive, it prompts a closer examination of
the alignment between reported profits and actual cash generation. A doubling of net income
should ideally be accompanied by a proportional increase in cash flow, but this may not be the
case. The changes in accounts receivable, accounts payable, and inventory are noteworthy. A
significant decrease in accounts receivable (-$706 million) and an increase in accounts payable
($150 million) might indicate alterations in the company's credit terms or payment practices.
Such changes could be potential red flags, requiring further investigation into their underlying
causes. Analyze the investing and financing activities to identify any unusual patterns. In the
case of Kelly Enterprises, Inc., the significant capital expenditures on property, plant, and
equipment might warrant an assessment of the strategic rationale behind these investments.
Additionally, changes in long-term debt and dividend payments could raise concerns about the
company's financial stability. Scrutinize the overall change in cash. In the provided case, the
$316 million decrease in cash in 2018 is a key red flag. Investigate the reasons behind this
decline and assess whether they align with the company's overall financial strategy. This shows
this method. Now for the Ratio method. The 1st step is liquidity ratios. Evaluate liquidity ratios
like the current ratio and quick ratio to assess the company's short-term financial health. The 2nd
step is profitability ratios. Examine profitability ratios such as the net profit margin and return on
equity. The 3rd step is solvency ratios. Assess solvency ratios like the debt-to-equity ratio to
gauge the company's long-term financial stability. The 4th step is efficiency ratios. Analyze
efficiency ratios like inventory turnover and receivables turnover to identify potential issues with
inventory management or the collection of receivables. The last step is comparative analysis.
9
Compare these ratios to industry benchmarks and historical performance. After investigating
here are some concerning areas in each step. The current ratio and quick ratio, assessing short-
term liquidity, exhibit values that need closer scrutiny. While net income doubled from $450
million in 2016 to $900 million in 2018, the net profit margin and return on equity should be
considered. The debt-to-equity ratio, measuring long-term financial stability, may indicate
potential concerns. Inventory turnover and receivables turnover ratios reveal potential
inefficiencies in inventory management and collections. Benchmarking these ratios against
industry averages and historical performance reveals variances that require explanation. This is
the investigation results.
CONCLUSION
Using a biblical lens, data-driven fraud detection uses data analytics to identify and address any
biases in fraud detection systems. Organizations strive to follow the biblical teaching found in
Proverbs 16:11, which states, "Honest scales and balances belong to the Lord; all the weights in
the bag are of his making." (NIV). These principles are motivated by the ideas of justice and
honesty. This biblical counsel emphasizes the need for fair and impartial methods for using data
to prevent fraud, in line with moral principles and encouraging honesty in financial operations.
10
REFERENCES:
Albrecht W., Albrecht C., Albrecht C., & Zimbelman M., (2019). Fraud Examination
Cengage Learning, Inc.
. Koch C., Okamura K., Benford’s Law and COVID-19 reporting, Economics Letters,
Volume 196, 2020, 109573, ISSN 0165-1765, https://doi.org/10.1016/j.econlet.2020.109573
Proverbs 11-16. New International Version. Bible Gateway. Proverbs 16:11 NIV -
Honest scales and balances belong to - Bible Gateway
Sánchez-Aguayo, M., Urquiza-Aguiar, L., & Estrada-Jiménez, J. (2022). Predictive Fraud
Analysis Applying the Fraud Triangle Theory through Data Mining Techniques. Applied
Sciences, 12(7), 3382. https://doi.org/10.3390/app12073382
TAMIMI, O., & ORBÁN, I. (2022). THE CORRELATION BETWEEN STATEMENT
OF CASH FLOWS, IAS 7, AND EARNINGS PER SHARE, IAS 33: A CASE STUDY AT
DAIMLER AG (MERCEDES-BENZ). Intelektine Ekonomika, 16(2)https://doi.org/10.13165/IE-
22-16-2-01
11
CASE EXHIBITS (TABLES)
CASE 5: Nantucket
| Supplier | Product | Price/Ton | Quantity | Total |
|------------------|---------|-----------|----------|---------|
| Woods ‘R’ Us | Oak | $157.00 | 2 | $314.00 |
| Woods ‘R’ Us | Cherry | $75.00 | 3 | $225.00 |
| Woods ‘R’ Us | Cedar | $125.00 | 1.5 | $187.50 |
| Woods ‘R’ Us | Spruce | $42.00 | 3 | $126.00 |
| Harris Lumber | Oak | $215.00 | 4 | $860.00 |
| Harris Lumber | Cherry | $115.00 | 8 | $920.00 |
| Harris Lumber | Cedar | $140.00 | 6 | $840.00 |
| Harris Lumber | Spruce | $80.00 | 9 | $720.00 |
| Lumber Jack’s | Oak | $158.00 | 1 | $158.00 |
| Lumber Jack’s | Cherry | $74.00 | 2 | $148.00 |
| Lumber Jack’s | Cedar | $124.00 | 2 | $248.00 |
| Lumber Jack’s | Spruce | $43.00 | 3 | $129.00 |
| Small’s Lumber | Oak | $156.00 | 3 | $468.00 |
| Small’s Lumber | Cherry | $76.00 | 3 | $228.00 |
| Small’s Lumber | Cedar | $127.00 | 1 | $127.00 |
| Small’s Lumber | Spruce | $41.00 | 4 | $164.00 |
12
CASE 8: Benford’s Law
AMOUNT DESCRIPTION CHECK
NO.
$235.65 Payment to U.S. West for phone bill 2001
$654.36 John’s Heating and Cooling for fixing A/C
in December
2002
$4,987.36 Sharky’s Used Car Dealership for Yugo
truck
2003
$339.13 Salt River Project for power in December 2004
$475.98 Arizona Department of Internal Revenue for
taxes
2005
$254.14 Grainger Corp. for power tools 2006
$504.17 Home Depot for outdoor carport 2007
$171.54 Steelin’s Consulting for help with computer
network
2008
$326.45 Payment to U.S. West for phone bill in
January
2009
$477.67 Bank of America for loan payment 2010
13
CASE 10: Kelly Enterprises:
| | 2018 | 2017 | 2016 |
+-------------------+---------------+------+------+
| Cash from Operations | | |
| Net income | $900 | $800 | $450 |
| Change in A/R | ($706) | ($230)| $25 |
| Change in A/P | $150 | $45 | $90 |
| Change in Inventory| ($50) | $15 | $25 |
| Depreciation | $105 | $90 | $65 |
| Net cash from ops | $499 | $690 | $655 |
+-------------------+---------------+------+------+
| Cash from Investing | | |
| Additions to PPE | ($950) |($690)|($790)|
| Proceeds from sale | $25 | $56 | $15 |
| Net cash from inv | ($925) |($634)|($775)|
+-------------------+---------------+------+------+
| Cash from Financing | | |
| Borrowings of LTD | $250 |($150)| $34 |
| Cash dividends | ($140) |($85) |($45)|
| Net cash from fin | $110 | $65 |($11)|
+-------------------+---------------+------+------+
| Increase (decrease) in cash | | |
| Total | ($316) | $121 |($131)|
