Senior Data Scientist at Revent Technologies Limited

About this Role

The Data Scientist will support the design, development and deployment of data-driven products, analytical models and insight solutions that strengthen our digital platforms, business intelligence capabilities and product decision-making. The role is responsible for turning data into actionable insight, building fit-for-purpose predictive and analytical solutions and supporting the development of scalable data products that create measurable business value across the our digital business ecosystem.

Key Responsibilities

Data Science, Analytics and Modelling

• Design, develop, test, and refine statistical and machine learning models to support digital products, business intelligence, forecasting, optimization, and risk monitoring.
• Translate business problems into analytical frameworks, modelling strategies, measurable outputs, and deployable insight products.
• Conduct exploratory data analysis, feature engineering, model selection, validation, and performance monitoring across structured and semi-structured datasets.
• Apply advanced analytical methods to uncover trends, patterns, risk signals, commercial opportunities, and operational inefficiencies.
• Build and evaluate predictive, descriptive, diagnostic, and prescriptive analytical solutions for internal and customer-facing use cases.
• Support model documentation, explainability, reproducibility, and controlled handover into business or technical workflows.
• Develop robust time-series forecasting models for business, product, operational, and risk-related use cases using both classical and machine learning/deep learning approaches.
• Apply relevant models such as ARIMA, SARIMA / SARIMAX, Prophet, XGBoost / LightGBM for time-aware forecasting, LSTM, GRU, Temporal Fusion Transformer (TFT) and other transformer-based or sequence-learning forecasting architectures as appropriate
• Develop and apply advanced survival analysis and time-to-event models to estimate the likelihood and timing of key business or risk events.
• Use and interpret relevant techniques such as Kaplan-Meier survival estimation, Cox Proportional Hazards model, Random Survival Forests, Gradient Boosted Survival models, DeepSurv and other modern survival or hazard-based modelling approaches where relevant.
• Select fit-for-purpose modelling approaches depending on data volume, temporal structure, explainability needs, and business constraints.
• Build forecasting solutions for multi-horizon, multivariate, and scenario-based prediction problems.
• Support model monitoring and recalibration where time-series behaviour changes over time.

Collaboration and Stakeholder Engagement

• Collaborate with internal stakeholders across business, operations, IT, product, innovation and strategy teams to understand needs and deliver analytical support.
• Present findings clearly and professionally, with strong attention to business relevance and practical recommendations.
• Support cross-functional initiatives involving analytics, intelligent automation and digital product enhancement.
• Escalate risks, data gaps and implementation challenges appropriately and in a timely manner.

Qualifications and Experience

• Bachelor’s degree in Data Science, Statistics, Mathematics, Computer Science, Economics, Engineering, Information Systems, or a related quantitative discipline.
• Approximately 6 years of relevant experience in data science, advanced analytics, machine learning or quantitative analysis.
• Experience working with business stakeholders to solve real-world problems using data.
• Experience in banking, financial services, fintech, trade, digital platforms or development finance is an advantage.
• Demonstrated experience in building analytical models and translating results into business insight.

Technical Skills

• Strong proficiency in Python for data analysis, machine learning, and model development.
• Good knowledge of SQL for querying and working with large datasets.
• Sound understanding of statistics, hypothesis testing, predictive modelling, and machine learning techniques.
• Strong understanding of time-series analysis, forecasting methods, temporal validation techniques and model performance evaluation.
• Experience with machine learning and forecasting libraries/frameworks such as scikit-learn, XGBoost, statsmodels, Prophet, PyTorch, TensorFlow, PyTorch Forecasting or equivalent.
• Practical familiarity with advanced sequence or temporal models, including Temporal Fusion Transformers (TFT) and similar deep learning architectures.
• Experience with data visualisation and dashboarding tools such as Power BI, Tableau, or equivalent.
• Familiarity with cloud, notebook or modern analytics environments is an advantage.
• Understanding of feature engineering, model backtesting, scenario simulation and basic model deployment concepts.
• Exposure to version control and structured development practices is an advantage.
• Behavioural and Functional Competencies
• Strong analytical and problem-solving capability.
• Good business judgement and ability to connect modelling work to commercial or operational value.
• Clear communication and presentation skills.
• Ability to work independently while managing multiple priorities.
• Strong attention to detail and quality.
• Collaborative mindset with the ability to work across teams.
• Curiosity, initiative, and willingness to learn.
• Professional maturity and ability to handle sensitive data responsibly. Professional maturity and ability to handle sensitive data responsibly.