Bill.com is a leader in financial process automation for small businesses and mid-size companies. Making it simple to connect and do business, the Bill.com Back Office Cloud digitizes, automates and simplifies legacy payment and financial processes. With an integrated, end-to-end platform, Bill.com leverages artificial intelligence to reduce manual work, and provides a cloud workspace to help run your business anytime, anywhere. The company partners with four of the largest U.S. financial institutions, more than 70 of the top 100 U.S. accounting firms, and major accounting software providers. Bill.com manages more than $70B in annual payment volume across ACH, virtual cards, checks, and international payments. The company has offices in Palo Alto, California and Houston, Texas. For more information, visitwww.bill.com or follow @billcom.
We are looking for a detail oriented, enthusiastic and dedicated risk data scientist to join Bill.com’s risk analytics and data science team with a focus on fraud and credit risks. The incumbent will be working on data science projects related to key risk department initiatives. The data scientist will own key projects associated with predictive fraud detection, transaction risk modeling and loss mitigation following Bill.com’s risk strategy roadmaps. This individual will also design experiments to understand the impact of customer experience when leveraging machine learning in complex risk strategy changes. This position requires a person who has experience with developing machine learning models and performing analytics preferably in risk domain.
Professional Experience/Background to be successful in this role:
Minimum 2 year of industry experience in data science
An advanced degree (M.S., PhD.), preferably in Statistics, Physical Sciences, Computer Science, Economics, or a related technical field
Strong track record of performing data analysis and statistical modeling using SQL, Python or similar tools
Mastery of a wide range of Machine Learning techniques, tools, and methodologies with a demonstrated capability to apply them to a broad range of business problems and data sources
Machine Learning techniques include clustering, classification, regression, decision trees, neural nets, anomaly detection etc.
Ability to clearly communicate complex results to technical experts, business partners, and executives
Comfortable with ambiguity and yet able to steer analytics projects toward clear business goals, testable hypotheses and action-oriented outcomes
Desirable to have experience solving problems related to risk using data science and analytics
Experience working with cross functional teams including product, engineering and operations
Expected Outcomes in 12 Months
Explore machine learning model application in different risk mitigation scenarios, including signup risk, transaction risk, network risk as well as credit risk
Work closely with the risk policy and operations team to identify relevant risk signals and develop predictive risk models
Follow risk team model development roadmaps to guarantee timely delivery of model governance related documentations
Evaluate third party vendor data quality and identify new opportunities leveraging various data elements to improve customer experience without incremental risk exposure
Competencies (Attributes needed to be successful in this role):