Transforming Facebook Finance Operations with AI
Facebook’s Enterprise Products Applied Research team develops AI solutions to enhance productivity for our Finance operations. In this talk, we present AI solutions we’ve developed for several stages of the order-to-cash cycle: credit management, collections prioritization and cash application. Managing credit limits for Facebook’s advertisers requires a large and rapidly growing number of credit decisions. We built a machine learning solution to assess advertisers for credit risk and help automate credit decisions. Our model has enabled Facebook to automate the majority of credit decisions while avoiding revenue loss from bad debt write offs as well as from credit outages for good accounts. We also use machine learning to prioritize collection activities. We proactively forecast probability of invoice bad debt write-off, and prioritize collections activities based on expected losses. This ML-based prioritization has led to faster payment. Finally we present an AI-based solution for automating cash application. We use OCR to automatically read remittance instructions, and apply payments accordingly. This automation has led to productivity savings and shorter cash application cycle time.
Key Takeaways, how FB uses AI to; 1) Automate credit decisions 2) Prioritize collection resources 3) Understand business documents
Julie Ward Drew is an Engineering Manager in Facebook’s Enterprise Engineering organization, where she builds AI & machine learning solutions for finance and compliance. She has over 20 years of experience applying optimization and machine learning to enable step-level improvements across a wide range of enterprise applications. Julie was awarded the 2009 Franz Edelman Prize for Outstanding Achievement in the Practice of Operations Research and Management Science by INFORMS. She received a Ph.D. in Operations Research from Stanford University and a Sc.B. in Applied Mathematics from Brown University.