The candidate will apply data mining techniques and conduct statistical analysis to large, structured and unstructured data sets to understand and analyse phenomena. Model complex business problems, discovering insights and opportunities through statistical, algorithmic, machine learning and visualisation techniques, working closely with clients, data and technology teams to turn data into critical information used to make sound business decisions. Execute intelligent automation and predictive modelling.
- Develop advanced ML (such as fraud etc) Credit scoring models for different business scorecards using ensemble algorithms in python.
- Conduct EDA, data extraction, data cleaning and documentation of created models
- Engage central team ensuring laid down best practices are followed
- Develop models which do not deviate too much from developed algorithms for Kenya
- Engage business stakeholders to glean from domain knowledge in creating fit for purpose algorithms
- Ensure codes are refactored for data engineering pipeline
- Engage assigned data engineers to promote developed models to production
- Engage scrum masters and project managers in a timely manner on a periodic basis to provide project updates
- Delivering projects within the allocated timeline
- Multitask by building more than one algorithm at each time
- Bachelors Degree in Information Technology/ Information Studies and/or any other relevant course
- Proven development experience in software and software engineering.
- Understanding of financial services data processes, systems, and products.
- Experience in technical business intelligence.
- Knowledge of IT infrastructure and data principles.
- Project management experience.
- Exposure to governance and regulatory matters as it relates to data.
- Experience in building models (credit scoring, propensity models, churn, etc.).
- Candidate should have 5 – 8 years of experience:
- Working with unstructured data (e.g. Streams, images)
- Understanding of data flows, data architecture, ETL and processing of structured and unstructured data.
- Using data mining to discover new patterns from large datasets.
- Implement standard and proprietary algorithms for handling and processing data.
- Experience with common data science toolkits, such as SAS, R, SPSS, etc.
- Experience with data visualisation tools, such as Power BI, Tableau, etc.
- Proficiency in application and web development. Structured and Unstructured Query languages e.g. SQL, Qlikview; SSIS SSRS, Python, JSON , C#, Java, C++, HTML