Senior Data Scientist

Company Description

Experian is the world’s leading global information services company, unlocking the power of data to create more opportunities for consumers, businesses and society. We are thrilled to share that FORTUNE has named Experian one of the 100 Best Companies to work for. In addition, for the last five years we’ve been named in the 100 “World’s Most Innovative Companies” by Forbes Magazine.

Experian is a global leader in information services, with the world’s largest credit bureau and other rich data assets in health, auto, marketing, rent bureau etc. Experian Decision Analytics (DA) supports clients by providing bureau-based scores, decisioning software and analytics products and services.

The Global Analytics and AI team is driving Experian’s efforts to productize analytics in each of its regions. The team has built a modern tech AI platform on the cloud, which will serve as Experian’s global platform for analytics products. This platform – Ascend Intelligence Services, is integrated with our data and decisioning systems, and hosts various analytics products spanning the end-to-end client lifecycle needs. This role will work cosely with various stakeholders to move this suite of products forward.

Job Description

The Senior Data Scientist will play a critical role in helping this transformation. The role is for an individual that is a blend of a ML Engineer and a data scientist that also has extensive experience in the financial industry and in particular credit risk modeling. The core responsibilities of him/her will include but are not limited to:

▪ Implementing prototypes of various Data Science Components/Apps

• Writing Python/Spark SQL code to implement prototypes from scratch
• Working closely with the core engineering team to move forward model build of the analytics products
• Suggesting ML techniques
• Building enhanced user-friendly dashboards for various steps in the pipeline
• Assisting in connecting new data assets to our end-to-end modeling platform

▪ Predictive Modeling Framework Development

• Building Generic Credit Risk and Propensity Scores
• Building highly specialized predictive models and overall process flows
• Supporting deployments of ML models
• Building reporting and monitoring frameworks

▪ Applying Data Science Knowledge to solve problems for clients

• Usage of Advanced machine learning techniques to solve ad-hoc client problems
• Bringing new ideas how to approach general problems in credit risk management
• Having fundamental knowledge in general processes around targeting, Fraud detection, acquisitions, Account management, collections
• Writing data pipelines / ETL for non-standard or new modeling use cases
• Build new dashboards and reports to provide insights to clients on model performance and impact, leveraging our proprietary BI toolkit
• Helping document methodologies, tool usage and business logic
• Testing new product features and algorithms and verify accurate implementation ahead of live release to our global client base
• Implementing bug-fixes and upgrades to Experian methodologies in credit-related business logic

Qualifications

Valuable leadership capabilities include

• Strong work ethic, needs to be a very driven individual and fine with tight timelines
• Shows strong passion and strong sense of urgency about reaching targets
• Out-of-box thinking
• Passionate about analytics, with a proven track record in applying analytics to address practical problems
• Clear, structured and organized communicator, and ability to write detailed specifications
• Proven track record coding data science applications relating to data, analytics and technology and in particular around credit risk
• Curious and stays up to date with the latest data science trends, and credible with data science experts and product experts
• Collaborative mindset, able to work with a range of business units, roles and external partners
• Willingness to get into the weeds, solve technical issues hands-on, and work directly with customers and developers as we drive early stage product growth
• Comfortable working with ambiguity and taking initiative

What your background looks like

• 3-5 years of industry specific experience
• 7-10 years of data science and data engineering experience
• Programming needs to come natural to the individual
• Fluent in at least one traditional programming language
• Extremely familiar with Python and SparkSQL and familiarity with modern data science and engineering technologies in general and common ML frameworks such as (MLlib, pytorch,
• sklearn, tensorflow all valuable) in particular
• Extensive experience with scrapping data and parsing unstruct