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
David Chi is an Applied Research Scientist in Facebook's Enterprise Engineering organization. He works on machine learning and artificial intelligence for internal applications used by finance, supply chain, and compliance organizations. He holds a bachelor's degree in engineering from UC Berkeley and a Ph.D. in engineering from Stanford University.