About the role

Our client aims to boost digital sales by leveraging advanced analytics and machine learning. This project focuses on developing and deploying propensity-to-buy models to enable personalized marketing and improve conversion rates. The assignment will be executed in collaboration with Team, which consists of data scientists responsible for building the models. You will work from the local Digital Marketing team, acting as a bridge between business needs and technical implementation.

To accelerate this, we’re looking for an experienced Data Analyst who partners with our Data Scientists in the Preparation and Exploration phases of model development and ensures business ready, reliable datasets.

Key Responsibilities & Deliverables

• Explore data to understand data sources, quality, potential features across key BB domains.

• Prepare model datasets: help Data Scientists with designing and building robust, well documented data pipelines.

• Translate business needs to data: act as the bridge between Business stakeholders and the data landscape; refine requirements and turn them into reproducible datasets.

• Raise data quality issues: surface issues early (completeness, consistency, timeliness) and coordinate fixes with data owners.

• Safeguard compliance: work within ING’s standards for data privacy, usage, and governance. Help with building the Risk Journey.

Required Background & Skills

• Strong SQL (must) and experience building analytical pipelines in a governed data environment (e.g., Databricks/BigQuery/SAS/Oracle).

• Proven track record in data preparation for DS/ML use cases (propensity/churn/CLV or similar).

• ING data experience is required, specifically with DM_CAN.

• Ability to translate business questions into data logic and present findings plainly to non technical stakeholders.

• Working knowledge of Python and/or SAS for dataset assembly and feature engineering is a plus.

Nice to have

• Experience with model building and Data Science is a pre.

• Understanding of Business Banking propositions (current accounts, payments, lending, bookkeeping, savings).

• Knowledge of data quality frameworks and basic MLOps/DS governance.