DataRobot > Case Studies > Valley Bank Reduces Anti-Money Laundering False Positive Alerts by 22%

Valley Bank Reduces Anti-Money Laundering False Positive Alerts by 22%

DataRobot Logo
Customer Company Size
Large Corporate
Region
  • America
Country
  • United States
Product
  • DataRobot AI Cloud
  • MLOps
  • AutoML
Tech Stack
  • Predictive Analytics
  • Automated Modeling
  • AI Lifecycle Optimization
Implementation Scale
  • Enterprise-wide Deployment
Impact Metrics
  • Productivity Improvements
  • Cost Savings
Technology Category
  • Analytics & Modeling - Predictive Analytics
  • Platform as a Service (PaaS) - Data Management Platforms
Applicable Industries
  • Finance & Insurance
Applicable Functions
  • Business Operation
Use Cases
  • Fraud Detection
  • Predictive Quality Analytics
Services
  • Data Science Services
  • Cloud Planning, Design & Implementation Services
About The Customer
Valley National Bank is the principal subsidiary of Valley National Bancorp. It is a regional bank with approximately $50 billion in assets. The bank operates many convenient branch locations and commercial banking offices across New Jersey, New York, Florida, Alabama, California, and Illinois. Valley is committed to providing the most convenient service, the latest innovations, and an experienced and knowledgeable team dedicated to meeting customer needs. The bank is also committed to helping communities grow and prosper, which is at the heart of Valley’s corporate citizenship philosophy.
The Challenge
Valley Bank, a regional bank with approximately $50 billion in assets, was facing a challenge in its Anti-Money Laundering (AML) department. The bank was dealing with an overwhelming volume of false positives in its effort to uncover money laundering activities across millions of transactions. The bank's AML team was seeking to reduce the manual work involved in predictive modeling. The process of creating models manually was time-consuming, taking weeks to complete. The bank was looking for a solution that could automate its fraud detection process and manage the volume of false positives in a realistic way.
The Solution
Valley Bank turned to DataRobot AI Cloud to automate its fraud detection process. The AI Cloud optimizes the entire AI lifecycle, helping to manage the volume of false positives without the need for data scientists on staff. The bank's model risk management team was involved from the start to validate the results. The bank fed predictions into its AML case management system and, alongside DataRobot data scientists, built and validated more than 100 models with a robust backtesting strategy. The bank also generated 175 features via DataRobot's automated Feature Discovery. During the trial, the bank reduced false positives by more than 30 percent. The bank's model risk management team was able to recreate those models successfully in the platform.
Operational Impact
  • Valley Bank was able to create new models or retrain models in a day, compared to weeks.
  • The bank was able to operate productively even when their only data scientist left the role, demonstrating the platform's ease of use.
  • The bank was able to save approximately 22 percent in total alert volume every month.
  • The number of alerts escalating to case increased by three percentage points.
Quantitative Benefit
  • Reduced false positives by more than 30 percent during the trial.
  • Saved approximately 22 percent in total alert volume every month.
  • Increased the number of alerts escalating to case by three percentage points.

Case Study missing?

Start adding your own!

Register with your work email and create a new case study profile for your business.

Add New Record

Related Case Studies.

Contact us

Let's talk!
* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.