£43,001 - £47,779 per annum, flexible hybrid working pattern (2 days per week in office), 35-hour week, 39 days annual leave (including statutory days), good pension scheme and other generous benefits

• Collect and analyse data from internal systems (tenancy, maintenance, finance) and external sources (e.g. census, public datasets).
• Clean, structure, and validate data to ensure accuracy and usability.
• Build models to forecast housing demand, rent arrears, and maintenance needs.
• Create dashboards and reports to communicate insights to non-technical stakeholders.
• Assess the impact of housing initiatives and recommend improvements.
• Use ML to optimise resource allocation, predict tenant behaviour, and automate processes like arrears risk scoring.
• Maintain data quality, security, and compliance with GDPR and other regulations.
• Work with housing officers and managers to translate operational needs into data-driven solutions.

• Industry certifications in data science or related fields (e.g., Microsoft Certified: Azure Data Scientist, Google Professional Data Engineer) or equivalent experience.
• Experience working as a data scientist, ideally within social housing, public sector, or a related industry.
• Experience working with social housing data systems (e.g., MRI, Northgate, Civica, or Orchard) and the ability to apply advanced analytics to operational challenges in housing (desirable).
• Demonstrated experience in using machine learning, predictive modelling, and statistical analysis to solve real-world problems.
• Expertise in statistical modelling, predictive analytics, clustering, classification, and regression techniques.
• Strong background in data mining, pattern recognition, and anomaly detection to improve service delivery.
• Proficient in Python, R, or other relevant programming languages used for data science.
• Strong skills in SQL and experience working with large databases and data warehouses.
• Ability to create intuitive and informative visualisations using tools such as Power BI, Tableau, or similar platforms.
• Familiarity with cloud-based data platforms (e.g., Azure, AWS) and deployment of models in a production environment.