Jumping on the Analytics Bandwagon

Transcription

1 Jumping on the Analytics Bandwagon How to Utilize the Data Within Your Organization s Systems to Gain Valuable Insight Data vs Information Garbage In Garbage Out Analytics to Intelligence 2 1

2 Background 4 2

3 Data vs Information Data Data is unprocessed facts and figures without any added interpretation or analysis. We serve 500,000 constituents. Company Data Examples Journal entries Customer lists Vendor lists Invoices Expenses Employee listings 3

4 Information Information is data that has been interpreted so that it has meaning for the user. The number of constituents that we serve has increased from 300,000 to 500,000 in 3 years" gives meaning to the data. Company Information Financial statements A/R Aging A/P Aging Sources of Funding Employee Retention 7 Information Data is raw, unorganized facts that need to be processed. Data can be something simple and seemingly random and useless until it is organized. When data is processed, organized, structured or presented in a given context so as to make it useful, it is called information. 8 4

5 Information from Data Any thoughts on what this is? 9 Garbage In Garbage Out 10 5

6 GI-GO Computers, since they operate by logical processes, will unquestioningly process unintended, even nonsensical, input data ("garbage in") and produce undesired, often nonsensical, output ("garbage out"). GIGO Data is not entered into the system at all PO Analysis 52% of records do not have an associated PO, which totals to $28m The next most used PO was PO 100, with $13m in total expenses, and 3% of all POs identified with an expense PO 210 had the most associated expense records, 2,397 for $10m Note: Names, dates, and amounts have been modified for presentation purposes. 12 6

7 GIGO Data is not entered in correctly The purpose/ usage of the field is not defined 13 Causation & Correlation Correlation: a relationship between two variables Causation: an act that occurs in such a way that something happens as a result Correlation does not imply causation 14 7

8 Correlation Analysis 15 Analytics to Intelligence 16 8

9 Types of Analytics Historical Descriptive Analytics: condense large amounts of data into smaller, more useful nuggets of information Diagnostic Analytics: determining if the correlation is causal Forward Looking Predictive Analytics: probability of different outcomes Prescriptive Analytics: integrate tried-andtrue predictive models into our repeatable processes to yield desired outcomes 18 9

10 Review the Data Review the data by skimming through it Performing various trial summarizations Identify anomalies or odd data Differences between Transaction Date and Bill Date range from 302 days (Transaction Date is 12/31/2011 & Bill Date is 2/28/11) to 654 days (TRANS Date is 8/13/10 & Bill Date is 6/7/12) Differences between Transaction date and Activity Date range from 745 days (TRANS Date = 5/23/13 & Activity Date is 4/28/11) to 360 days (TRANS Date is 12/31/11 to Activity Date 12/31/12) Differences between Bill Date and Activity Date range from 798 days (Bill Date of 7/31/13 to Activity date is 5/12/11) to 300 days (Bill Date of 2/28/11 to Activity date is 12/31/11) Reversing Entries. The amounts do negate out, however, the notation under the reversing entry is update with actual invoice amount, but the Transaction Date and Activity Date for both the entry and the reversing are the same dates. TRANDT BILLDT ACTVDT VEND_NAME INVOICE Total Descr 1/18/2010 2/18/2010 1/18/2010 ABC Company PrePay 2,000,000 Prepay to Secure Date 1/18/2010 2/18/2010 1/18/2010 ABC Company PrePay 2,000,000 Update w/actual inv amt 19 Accounts Payable - Input Check Register Vendor Master Invoice Master Employee Master 10

11 Accounts Payable Analytics Check Gaps and Duplicates Vendors Lacking Key Data Duplication of Key Data Employees Set up as Vendors Vendor Payments Dormant to Increased Activity Rounded Amount Payments Duplicate Payments Vendor, Amount Vendor, Amount, Date Cash Payments Payments below threshold approvals Vendors with Consecutive Invoice Numbers Trend Analysis on Vendor Payments 21 AP Example Check Register Gaps Gap_Start_ Gap_End_ Number_Items Check Check _Missing Multiple Vendor Records for 1 Vendor VendorID VendorName CheckAmount #Of Checks VendorAddr1 VendorCity VendorState 1 Company A 7, PO BOX 8 Anywhere TX 2 Company A 74, PO BOX 1 Anywhere TX 56 Company B PO BOX 3 Anywhere TX 77 Company B PO BOX 3 Anywhere TX 9879 Company C Main Here TX 23 Company C PO BOX 3 Here TX 345 Company D 5, PO BOX 141 Here TX 456 Company D 11, PO BOX 149 Here TX 234 Company E 1, PO BOX 32 Here TX 8421 Company E 52, Here TX 215 Company F PO BOX 30 Anywhere TX 8753 Company F 30, PO BOX 26 Elsewhere WA Missing Tax ID Vendor 1099 Vendor NumberOf VendorID VendorTaxID VendorName Status Status Check Amount Checks Company A Y T Company B Y T Company C N 1,283, Company D N T 3, Company E N T 20, Company F N T 19, Company G N T 9, Company H N T 61, Company I N Company J N T 4, Refunds A N 25, A/R Refunds N T 303, PY Zero Payments, CY Payments VendorID VendorName CheckAmount 2016 total NumberOfChecks A Sparrow 27, B Eagle 13, C Mockingbird 6, D Hawk 101,

12 Payroll Noted 1 employee record with with no name or address. No payroll disbursements were made. 5 employees with PO Box as their addresses. Only 10 salaried employees who were paid during the year. Calculated an average hourly rate for these EE and they were all paid a consistent rate for all pay periods. 15 employees who met scope of GrossPay>=$10,000 and Deduction Ratio <.1 23 Purchase Cards Several charges on the same day for an amount slightly under the single transaction limit. Transactions occurring on weekends or holidays. Duplicate transactions made by the same user on the same day Vendor Analysis

13 Tools Microsoft Excel Microsoft Access Database ACL and IDEA 25 Questions? Reema Parappilly, CISA Senior Manager, IT Advisory Jennifer Ripka, CPA Senior Manager, Audit