Associate Data Scientist

We are the leading global information services company, providing data and analytical tools to our clients around the world. We help businesses to manage credit risk, prevent fraud, target marketing offers and automate decision making.

We also help people to check their credit report and credit score and protect against identity theft. In 2020, for the sixed consecutive year, Experian has been named to Forbes Magazine’s Top 100 list of the “World’s Most Innovative Companies.”

We employ approximately 17,200 people in 44 countries and our corporate headquarters are in Dublin, Ireland, with operational headquarters in Nottingham, UK; California, US; and São Paulo, Brazil.

At Experian, we are committed to building an inclusive culture and to creating an environment where people can balance successful careers with their commitments and interests outside of work. Our flexible working practices support our belief that this balance brings long-lasting benefits for our business as well as our people. Some roles lend themselves to flexible options more than others, and if this is important to you, we are open to discussing agile working opportunities during the hiring process.

Position Title: Associate Data Scientist

We're currently looking for an Associate Data Scientist to join the R&D Team, part of our Analytics Center of Expertise, focused on rolling out Trusso, our cutting-edge Machine Learning based transaction categorization engine.

Responsibilities:
Oversee and facilitate the training of a range of Machine Learning models,
Build new ML-based solutions from scratch based on the newly available data
Evaluate the quality of the trained models, using existing and also new measures
Report on the current and historical state of our models’ performance, along with issues and progress,
Incident resolution: Low accuracy troubleshooting, mis-categorisation issue analysis
Maintenance and improvement of the existing model development pipeline
Produce ad-hoc analysis/investigations on the modelling pipeline
Document parts of the modelling/testing process

The successful candidate will have:
A degree (BSc level) at a numerical discipline, such as Computer Science, Maths, Statistics, Physics, etc.
Strong grasp of probability, statistical inference, optimization algorithms, linear algebra, and calculus.
Understanding of how and when to apply key analytical approaches including regression analysis and machine learning
Strong grasp of techniques for model cross-validation and penalizing unnecessary complexity, including regularization, in-sample vs out-of-sample.
Ability to write near-production-level code in at least one general purpose programming language (e.g. Python, C++).
Flexible and adaptable to learn and understand new technologies
Demonstrable analytical and problem-solving abilities, coupled with an enquiring mind and the ability to learn quickly
A keen eye for detail, good at spotting problems and quickly proposing solutions.
Strong verbal and written communication skills (fluency in English)
Any of the following abilities and skills will be considered an advantage:
Experience with natural language processing techniques and tools for the parsing of unstructured data.
Experience with deep learning and other advanced modeling approaches to extract and automate insights from data.
Fluency with statistical significance tests and Monte Carlo simulation.
Experience with automation packages, such as Luigi and make
Exposure to Linux.
The health and wellbeing of our people is a top priority.

That’s why if you join us we will provide you with the benefits which fit your needs through all the stages of your life.