Skip to main content

Reinventing digital payments using data and ML


Reduction in operating costs


Infrastructure cost reduction


Improvement in ML experimentation

coins ph header

“With the Databricks Data Intelligence Platform, our operational costs have reduced by about 70% due to more efficient cluster management.”

— Dmitry Ustimov, Data Architect,

As a key digital payments platform in the Philippines, needs to be able to perform accurate, insightful financial audits and prevent fraud — in real time. With more than 10 million customers accessing digital payment services, such as local and international remittances, bill payments and online shopping, needed to find a way to move beyond development operational (DevOps) processes and address more advanced business challenges. With Databricks, was able to harness richer data insights to identify new functional opportunities, delivering ML-powered fraud detection and anti-money-laundering solutions at greater speed while optimizing financial reconciliation.

Rigid legacy systems that hindered ML experimentations

At, their mission has always been to leverage data and AI to prevent fraud and money laundering while performing financial audit and reconciliation operations.

“Our previous analytics system was built on Amazon and leveraged Elastic MapReduce (EMR). It required a significant effort from our data team to maintain and use the platform for development operational tasks,” said Dmitry Ustimov, data architect at turned to Databricks to simplify infrastructure management and provide a unified approach to data and analytics, enabling them to harness richer insights for smarter decision-making and accelerate the development of ML-powered models to address business challenges.

Unifying data and ML drives innovation and efficiency

With Databricks as their unified platform for data and ML, the data team at can now optimize daily DevOps tasks while shifting their focus to generate value for the business, in key areas such as fraud detection and anti-money laundering via ad hoc analytics.

Using Delta Lake to ingest large volumes of data in real time, data engineers at are able to bring greater reliability to the data lakes and get up-to-date insights to develop more robust and scalable data pipelines. This accelerates the development of data modeling prototypes by their data scientists. The platform provides automated cluster management, allowing the data team to effectively create data clusters specifically tailored for troubleshooting and round-the-clock monitoring activities without taxing data engineering resources.

Databricks’ interactive and easily maintained notebooks allow various data teams — data engineers, data scientists or business analysts — to leverage the platform and collaborate for data preparation, simple analytics and prototyping new models. This is expedited with the pre-created, self-help features within the notebooks.

“Collaboration with cross-functional teams is facilitated with the sharing of high-quality reports through integration with third-party business insight tools such as Metabase,” explained Ustimov. “It further simplified technically-advanced Databricks capabilities to enable less technically-skilled business users to easily extract actionable insights from the data, such as enabling the finance team to access consistent financial data for accurate reporting.”

MLflow simplifies and streamlines the ML lifecycle, allowing data teams to easily track ML experiments and quickly develop new prototypes to address fraud detection. In addition, the platform enables teams to run experiment jobs with standardized analytics. By doing so, the team is able to roll out new features or rule sets for anti-money-laundering compliance.

Another benefit of implementing the Databricks solution is having experts readily available to address the issues of the data team.

“We asked for recommendations on the best way to architect a streaming ETL pipeline in order to provide optimal real-time insights in the most cost-efficient manner. We were pleased to receive a helpful response within hours,“ said Ustimov.

Reducing operational costs by 70%

The Databricks Data Intelligence Platform has enabled to effectively identify and deliver new solutions to enhance the overall financial services offered with a more compact, nimble and agile data team.

“Thanks to faster big data experiments, enabled by Databricks, the time taken to market for new features in machine learning–based projects has been reduced from weeks to days or even hours,” said Ustimov.

The Databricks Data Intelligence Platform is more stable, allowing data refresh to occur in near real-time and providing the security and compliance teams with real-time notifications for proactive intervention.

Moreover, with automated cluster management on Databricks, infrastructure costs and operational costs have been reduced by about 50 percent and 70 percent, respectively, due to ease in upscaling and downscaling of clusters and experiments.

Moving forward, the data team at has started leveraging Databricks as the backbone for their business insights platform, tapping the potential of Delta Tables as the primary data source for near real-time analytics. They have also begun utilizing ML experimentation to boost’s fraud prevention and anti-money-laundering capabilities, exploring advanced solutions such as predictive analytics and user-friendly recommendation engines. This gives the data team at a level of satisfaction and confidence to tackle any data challenge thrown at them in the future.