Field Data Scientist Internship - Customer Success Team

About DataVisor

DataVisor is the world’s leading AI-powered Fraud and Risk Platform that delivers the best overall detection coverage in the industry. With an open SaaS platform that supports easy consolidation and enrichment of any data, DataVisor's solution scales infinitely and enables organizations to act on fast-evolving fraud and money laundering activities in real time. Its patented unsupervised machine learning technology, advanced device intelligence, powerful decision engine, and investigation tools work together to provide guaranteed performance lift from day one. DataVisor's platform is architected to support multiple use cases across different business units flexibly, dramatically lowering total cost of ownership, compared to legacy point solutions. DataVisor is recognized as an industry leader and has been adopted by many Fortune 500 companies across the globe.

Our award-winning software platform is powered by a team of world-class experts in big data, machine learning, security, and scalable infrastructure. Our culture is open, positive, collaborative, and results-driven. Come join us!

About the Role

At DataVisor, we pride ourselves in taking a data-driven approach to provide industry best risk detection and prevention results to our customers. We leverage Unsupervised Machine Learning, Supervised Machine Learning, Advanced Rules and Tuning, to achieve a high capture rate of fraud attacks and very low false positive rate.

As a Field Data Scientist Intern on the Customer Success team, you will work directly with real-world industry data, understand the data structure and data schema, research the customer’s specific business problems, analyze the patterns within the datasets that could be utilized to describe and capture the fraud attacks, and come up with effective detection strategies.  You’ll collaborate with our Technical Account Managers (TAMs), Solution Data Scientists, and the fraud teams on the customer side, to develop, test, and implement new strategies or adjustments for existing rules, in our Risk Decision Engine. You will use manual review feedback and labels to evaluate the effectiveness of the strategies, and build dashboards to track the overall trends and detection performance metrics. If you have a passion for big data mining, real-world problem research and solving, and data-driven solution building, we’d love to hear from you!

Responsibilities

• Research and understand real-world fraud problems e.g. Scam and Check Fraud. 
• Understand and document the data structure, data flow and data schema of the relevant data needed to solve the problems
• Analyze large-scale datasets to identify fraud attack patterns and attack evolutions.
• Research and understand the tools and data signals needed to help solve the problems, e.g. Unsupervised model score, Supervised model score, 3rd party data signals. 
• Conduct feature engineering and strategy building to capture the patterns identified. 
• Test the features and strategies created and quantitatively evaluate their performance
• Present the results to TAMs and the customers, and gather feedback.
• Conduct strategy tuning and iterations based on the feedback gathered.
• Implement the finalized strategies to production, and build dashboards to track and monitor performance.

• U.S. Citizen (required)
• Currently pursuing, or recently obtained a BS/MS in Data Science, Statistics, Machine Learning, or a related field.
• Proficiency in at least one object-oriented programming language (e.g., Python, Java, C++).
• Proficiency in using SQL queries to conduct data joining and pattern analytics
• Strong foundation in data structures and algorithms; ability to write efficient, optimized code.
• Strong analytical, problem-solving, and critical thinking skills.
• Excellent project management and communication abilities.
• Familiarity with big data technologies (e.g., Hadoop, MapReduce, Spark) is a plus.