Case Study: AI GL Reconciliation for a Major Credit Card Provider
Updated: 1 day ago
In short: A Tier 1 credit card provider was matching more than 50,000 bank transactions a day to its general ledger, with a large share left for manual work. Matchimus raised the one-to-one match rate from 73.8% to 92.4% and the overall match rate from 62.8% to 81%, cutting daily manual matches from more than 15,000 to fewer than 5,000.
In the fast-paced world of credit card transactions, efficiency and accuracy are essential. For a global capability centre of a Tier 1 credit card provider, daily General Ledger (GL) to bank statement reconciliation posed a significant challenge.
This case study explores how Operartis’ Matchimus, leveraging AI in the financial industry, transformed their reconciliation process, dramatically reducing manual effort and improving match rates.
The Challenge: Manual Matching Overload
The credit card provider faced a substantial reconciliation burden, dealing with over 50,000 daily bank transactions requiring matching to GL entries.
Their existing solution, a market-leading data integrity reconciliation platform, utilised 23 crafted rules. However, this yielded a match rate of only 62.8% for overall GL to bank transaction matches, and 73.8% for 1-1 transactions, on their suspense and clearing accounts.
This left a staggering 15,000+ transactions requiring manual matching daily. With each manual match taking approximately two minutes, the 150-strong reconciliation team spent 500 hours – over 30% of their daily effort – on this task. The sheer volume of manual work led to the risky practice of "lumping together" unrelated transactions to save time, creating a potential audit nightmare.
As highlighted on the Operartis' platform, the "complexities of financial data" and the "need for accuracy" are key challenges in reconciliation. This credit card provider was facing these challenges head-on.
The Solution: Matchimus and the Power of AI in the Financial Industry
Recognising the limitations of their rules-based approach, the credit card provider sought a more intelligent solution. They turned to Operartis’ Matchimus, a platform powered by AI in the financial industry, designed to automate and optimise reconciliation processes.
Matchimus was trained using a single customer extract of one week’s worth of production data.
The system automatically pre-processed the data, including intelligently splitting apart the large, grouped manual matches into more granular, accurate matches. This automated training process allowed Matchimus’s machine learning algorithms to understand the unique patterns and structures of the provider’s reconciliation data.
The Results: Dramatic Improvements in Efficiency and Accuracy
The implementation of Matchimus yielded measurable results:
Increased Match Rates: For 1-1 matches, the match rate surged from 73.8% to 92.4%. Across all aggregation types, including ad-hoc groups, the match rate improved from 62.8% to 81%.
Significant Reduction in Manual Matching: The daily manual matches decreased by over 10,000 transactions.
Substantial Time Savings: With a two-minute reduction per manual match, the provider realised savings of over 300 user hours per day, equivalent to 40 full-time employees (FTEs).
Key Statistics:
Initial 1-1 Match Rate: 73.8%
Matchimus 1-1 Match Rate: 92.4%
Initial Overall Match Rate: 62.8%
Matchimus Overall Match Rate: 81%
Reduction in Daily Manual Matches: > 10,000 transactions
Daily Time Savings: > 300 user hours (40 FTEs)
The Impact: Efficiency, Accuracy, and Reduced Risk
The implementation of Matchimus delivered significant benefits:
Increased Efficiency: The dramatic reduction in manual matching freed up substantial resources, allowing the team to focus on higher-value tasks.
Improved Accuracy: Higher match rates and the elimination of "lumped" matches enhanced data integrity and reduced audit risk.
Cost Savings: The reduction in manual effort translated to significant cost savings, equivalent to 40 FTEs.
Reduced Audit Risk: The elimination of grouped matches improved audit compliance.
AI in the Financial Industry: The Future of Reconciliation
This case study exemplifies the transformative power of AI in the financial industry. By automating complex reconciliation processes, financial institutions can achieve significant improvements in efficiency, accuracy, and risk management.
As the financial industry continues to grapple with increasing data volumes and regulatory pressures, AI-powered solutions like Matchimus will play a crucial role in driving innovation and operational excellence. Operartis’ platform demonstrates the power of AI to transform reconciliation and help financial institutions to achieve their strategic objectives.
By embracing AI, financial institutions can not only improve their bottom line but also enhance their ability to navigate the complexities of the modern financial landscape.
Frequently asked questions
What problem did the credit card provider have?
Its rules-based GL-to-bank reconciliation left thousands of transactions a day for manual matching, including ad-hoc groups that rules could not handle.
What results did Matchimus deliver?
The one-to-one match rate rose from 73.8% to 92.4%, the overall match rate from 62.8% to 81%, and daily manual matches fell from more than 15,000 to fewer than 5,000.
Did the provider replace its reconciliation system?
No. Matchimus worked alongside the existing setup, learning from historical matches and taking on the transactions the rules could not match.
What's Next?
Don't settle for the limitations of manual reconciliations. Operartis offers a glimpse into the future of financial services with machine learning in the credit card industry – a future powered by data-driven insights and AI.
Let us help you transform reconciliations from a burden into a strategic advantage.
Get a quote personalised to your use case with our Proof of Value (PoV) assessment. We'll measure the match rate improvement on your reconciliation data and send you an Uplift Report detailing your ROI before you commit to purchase.
Let's talk it over – book a Proof of Value to increase efficiency, improve exception management, reduce costs, and enhance visibility into your financial data.
