Abhishek Chatterjee, Founder and CEO
Reconciliation processes have become increasingly challenging in the financial sector considering the lengthy and complex on boarding processes, a growing number of data sources, and higher transaction volumes. Besides, the combination of changing regulatory requirements and the emergence of new asset types and structured deals with complicated calculations demand an increased focus on the reconciliation process, making it a stressful task. Despite combining custom rules model and human intervention to overcome obstacles, exception handling and adjustment prediction remains laborious and costly. Although there are solutions in the market that are run using RPA, they offer minimal support when it comes to complex matching and exception handling. Also, they need be modified to accommodate the varying business and regulatory requirements. Here, solutions that maximize efficiency and effectiveness in the reconciliation process can bring a world of difference to organizations. And this is precisely what Tookitaki offers through its endto- end, machine learning-powered reconciliation software application— Tookitaki Reconciliation Suite(RS).
Built on proprietary machine learning algorithms, RS is a scalable, reconciliation platform that has specific modules to support automated matching and exception handling. While developing RS, Tookitaki adopted a unique architecture where it carefully separates the machine learning and business workf lows. “Our platform utilizes machine learning models to understand and learn from previous reconciliation cases, and then predicts both known and unknown exception cases without human intervention,” explains Abhishek Chatterjee, founder and CEO of Tookitaki. The company’s comprehensive solution performs end-to-end reconciliation faster and offers automatic exception/ break management and adjustment predictions with high accuracy.
“Our matching engine uses ML and distributed systems to rif le through billions of transactions and enhances the match performance and accuracy, without manual rules or updates,” says JeetaBandopadhyay, cofounder and COO of Tookitaki. “Automation has saved significant time and costs for firms in rolling out and managing huge volumes of reconciliations,” she adds. Equipped with advanced Machine Learning techniques that define existing and new matching rules, RS’s matching module handles complex match cases and overcomes matching inefficiencies. On the other hand, the exceptions handling engine successfully resolve the exceptions by improving break classification according to a client’s business requirements.
Our platform utilizes machine learning models to understand and learn from previous cases or patterns, and then predicts both known and unknown exception cases without human intervention
It can automatically build exceptions models from historical data generated by the rules-based system. The RS solution provides a detailed audit trail to understand the rationale behind a break or matchcase and address it accordingly.
Besides Tookitaki RS’s capabilities in reconciliation and rapid onboarding, it also offers automated matching, efficient break detection, and resolution. What keeps Tookitaki ahead of its competition is its detailed audit trail supported by a patent-pending ‘explainability’ framework, automated model management that helps create ML models easily, continuous learnig keeps the performace of matching and exception handling engine intact with new data types and increase in data volumes and a strong analytics layer that brings detailed insights to drive business outcomes. Abhishek points out that Tookitaki RS covers sectors such as capital markets, banks and corporates as well as support asset classes like equities, forex, cash, commodities, and derivatives. He believes that the platform’s efficiency in handling data from multiple sources, streamlined reconciliation processes, ability to reduce operational costs, and associated risks along with enhanced compliance and scalability will drive increased demand for the solution. Historically, Tookitaki has been able to showcase 90% better matching coverage than rules-based systems and reduce break resolution time by about 50%.
To further illustrate Tookitaki’s capabilities, Abhishek narrates an instance where a Europe-based global bank’s short-term lending and borrowing business unit wanted to improve its reconciliation process by leveraging the potential of ML. The global bank used RCG, which is the process of conducting reconciliation between accounting and inventory data to identify the discrepancies caused due to manual or system errors. The exception handling in the system was managed by writing rules to identify the cause of the break. The bank wanted to automate its break reconciliation process and approached Tookitaki for its Reconciliation Suite. With the implementation of the Tookitaki RS, the bank was able to update its break resolution system with more comprehensive rules. The new system enabled the automatic evolution of models according to the changing data patterns and achieved high accuracy levels. Furthermore, Tookitaki improved the quality and reduced the time of the investigation process while establishing a detailed audit trail.
The future looks promising for Tookitaki as the company has raised almost $20.5 million in funding, of which, a large portion will go toward strengthening the company’s research and development capabilities. In order to meet the rising demand for Tookitaki’s solutions, the company also plans to increase its workforce. As a part of expansion, Tookitaki intends to widen its client base in APAC and target financial institutions in Europe and North America.