How to plug leakages in your Procure to Pay - Part 2

In my last blog , I spoke about the magnitude of damage P2P fraud can cause to the organization and the need to address the problem with a different mindset with a more data driven approach.

Let me list out some common risk factors in the payments space that we see today:

Delayed payments can erode supplier relationship
Early payments can have an adverse impact on working capital and cash flow
Failure to issue Purchase Order for each order
Duplicate payments or excess payments
No confirmation on matching deliveries/ goods received match with contract terms
Approvals received immediately after PO creation (pointing toward maker-checker collusion)
Payments to shell vendors/ blacklisted vendors
Suspicious vendor invoices, including consecutive invoice numbers and non-sequential invoices
Errors (intentional or mistakes) in address, vendor name, amounts etc.
Payments just below approval limits
Payments for round dollar amounts

As is conceivable, some of these could be due to human errors and others with an intent to deceive. While traditional approaches help in uncovering some gaps, they suffer from some inherent shortcomings as discussed in one of our earlier posts . Some of these shortcomings are high false positives, inability to uncover newer anomalies and recognize patterns in large datasets, not learning from feedback.

We have seen significant upside potential through use of data analytics and machine learning in fraud detection. Since anomalies are rare and considerably different from each other, pre-defining what we are looking for turns out to be infeasible. We approach this by letting data define the boundaries of normal behavior and flag the ones that fall out/ look abnormal. Additionally, by scoring the red flags, we can set priorities for the investigation team, channelizing their efforts to higher order tasks.

Below are some of the outcomes from our implementations in Procure to Pay:

Identified duplicate amounting to 0.63% of total Accounts Payable for a retail chain
Prioritized red-flags to reduce back-office team’s efforts by 72% for a hi-tech company
Detected 12 high risk transactions from 20 million invoices for a retailer
Identified 5 fictitious expense claims by co-relating HR, geo-location and task assignment details for a consulting firm

These outcomes demonstrate the potential of Artificial Intelligence (AI) in elevating the P2P function to one of strategic importance and hence, in enabling the organization to achieve competitive advantage over its peers.

Service Offerings

Service Offerings

Client Themes

Client Themes

How to plug leakages in your

Procure to Pay - Part 2

Service Offerings

Industries

Cloud

Cybersecurity

Digital

EngineeringNXT

HOLMES

Contact Us

About Wipro

Careers

Location

Leadership

Investors

Innovation

News and Events

Blogs

Analyst speak

Products & Platforms

Partner Ecosystem

Sustainability

Contact Wipro