Job Summary
To perform risk and securities administrative duties, through the execution of predefined objectives as per agreed standard operating procedures (SOPs).
Job Purpose
The role holder is responsible for applying data mining techniques, doing statistical analysis, building high quality prediction algorithms, developing analytical reports and devising analytical solutions to use cases and data science problems. This will involve the ability to create sophisticated, value-added analytic systems that support revenue generation, risk management, operational efficiency, regulatory compliance, portfolio management, and research.
Key Accountabilities
Perform statistical analysis, deploying models on large data sets.
Conduct exploratory data analysis
Demonstrate strong understanding of agile delivery.
Develop code with Spark via PySpark or SparkR
Perform queries, aggregations, joins, and transformations using Spark, Hive, and Pig.
Develop new data sets using feature-engineering techniques.
Deliver value by creating functions, classes, and packages to automate processes and workflows for production deployment.
Evaluates user request for new/modified programs to determine feasibility, cost and time required, compatibility with current system, and computer capabilities.
Transform large, complex datasets into pragmatic, actionable insights.
Leverage data to identify, quantify and influence tangible business gain
Implement analytical model designs, perform any restructuring required, and review dataset implementations performed by the data engineer and BI developers.
Selecting features, building and optimizing classifiers using machine learning techniques
Data mining using bank selected data mining tools
Enhance data collection procedures to include information that is relevant for building analytic systems
Processing, cleansing, and verifying the integrity of data used for advanced analysis
Doing ad-hoc analysis and presenting results in reports, dashboards and charts
Creating automated anomaly detection systems and constant tracking of its performance
Implement statistical data quality procedures or test-driven approach for quality assurance
Challenge ideas and methods while working together with talented, highly skilled team members.
Design, create, interpret and manage large datasets to achieve business goals
Design, build, and maintain various parts of the data warehousing with respect to requirements gathering, data modelling, metric establishment, reporting production, and data visualization.
Gather and process raw, unstructured data at scale into a form suitable for analysis then consolidate into the data warehouse in order to perform Business Intelligence and advanced analytics.
Evaluate datasets for accuracy and quality using statistical data quality procedures, software, or test-driven approaches that ensure quality assurance and solve any issues, which may arise.
Improve data foundational procedures, guidelines and standards and develop best practices for data management, maintenance, reporting and security.
Conduct performance tuning to be able to optimize the application of statistical models and scripts
Develop and maintain documentation/manuals on models developed, reports generated and statistical solutions devised.
Carry out technical user training as required to enable users interpret Data Science solutions
Ability to take personal responsibility and accountability for timely response to client queries, requests or needs, working to remove obstacles that may impede execution or overall success.
Assist in developing and implementing a program of continuous improvement of Data processes through a cycle of analysis of existing systems, processes, and tools, identifying areas for improvement, and implementing high-impact changes, and getting feedback from stakeholders.
Understand Key Performance Measures and Indicators that drive company performance measurement, reporting, and analytics across functions and understand how these metrics and measures align and track against overall business strategies, goals and objectives.
Work with Business Customers to understand business requirements and implement solutions and with business owners to develop key business questions and to build datasets that answer those questions.
Assist to analyze business/use case requirements from BI analysts to determine operational problems, define data modeling requirements, gather and validate information, apply judgment and statistical tests and develop data structures to support the generation of business insights and strategy;
Provide test interfaces for users to test the reports and dashboards before being put on the production environment.
Preferred Qualification
B-degree in Mathematics/statistics, data sciences or related quantitative fields is preferred (or equivalent on-the-job experience).
Preferred Experience
1-3 years Technical experience in data science.
Knowledge & Skills
Data-oriented personality
Knowledge of agile software development process and performance metric tools
Experience extracting and cleaning text in different formats e.g. HTML, pdf files
Proven ability to collaborate with other team members across boundaries and contribute productively to the team’s work and output, demonstrating respect for different points of view. Able to use strong interpersonal and teamwork skills to cultivate effective, productive client relationships and partnerships across organizational boundaries.
Knowledge on the Hadoop Data Platform and using Scala for big data analysis
Proficient at queries, report writing and presenting findings
Knowledge of ETL and data integration tools
Knowledge of merging technological trends in programming languages and other programming tools
Apply via :
absa.wd3.myworkdayjobs.com
