Analyst Advanced Analytics wanted: Apply Here

0

Analyst Advanced Analytics wanted: Apply Here

Analyst Advanced Analytics (Everyday Banking/Personal Lending) – JHB(Job Number: 90232670)

Description
The purpose of this role is to provide advanced analytical solutions to facilitate effective decision-making by business stakeholders within the business environment at a strategic and tactical level. The engagement starts at an identified business problem, moves to exploratory analytics and ultimately models the impact of a proposed solution. Provide guidance on what analytical techniques provide a best fit. This role exists to engage with the Business and elicit requirements while facilitating the understanding of the value of MI, reporting and BI within the Business environment and engaging with the MI developers to deliver on Business value within the MI framework and governance.

Key Responsibilities
Accountability: Develop Predictive Analytical Solutions
Determine the business objective or purpose wherein the analytical solution is going to be utilized. Meet with business stakeholders, where necessary to discuss and clearly define the scope of the analysis, to ensure that relevant & value-add analytical solutions are developed to aid effective decision making by the business
stakeholders.

Utilise various data mining techniques and methodologies to produce the analytical solutions required to assist business stakeholders. This may necessitate the development of statistical models to discover the variables or factors that are correlated with/accountable for a particular trend or outcome. Statistical modelling will also be utilized to predict or forecast the probabilities of certain outcomes being realised.
Develop extraction programmes to extract the data from the relevant data bases and undertake data preparation of the extracted data in order to correct problems. This involves inter alia checking for and correcting the following data issues ; (i) univariate normality, (ii) multivariate normality, (iii) homoscedasticity, (iv) multi-collinearity, (v) relative variances, (vi) outliers, (vii) missing data.

Build the statistical model: 1) build the initial model on the training data set, 2) use the validation data set to adjust the initial model, 3) apply the model on the test data set to gauge the likely effectiveness of the model. Undertake technical assessment of the statistical model to determine the error rate (false negatives and false positives) or residuals (difference between the predicted score and the actual measure score). Utilise a confusion matrix or lift chart where appropriate. Run the statistical model on the relevant target population, and score all entities in the target population.
Profile and analyse the data to identify significant trends and patterns that would serve to create insight for business stakeholders. Develop professional presentations of these analyses and present findings and recommendations to the business stakeholders.
Prepare technical documentation on the SAS extraction programme and the statistical modelling process followed. Include the relevant SAS procedures (PROCs). Handover the technical documentation and SAS programme for automation by MI area and other areas identified.
Proactively analyse and identify problem areas and plan/implement steps for process improvement to impact quality and production based on results of analytics work.
Support the reverse engineering of existing solutions where required.
Accountability: Business Engagement and Relationship Building
Build effective working relationships with business stakeholders to develop a detailed understanding of their business imperatives and objectives.
Maintain an interactive process with stakeholders as the analytical solution is being developed – present and receive feedback on work-in-progress.
Perform a consultancy role with business stakeholders. Present the final analytical outputs to stakeholders and assist in interpreting the results and providing advice & recommendations on the implementation of actions.
Educate users where required on the design or how to utilise the solution.

Accountability: Continuous Self-Development and Growth
Undertake research into data mining case studies – analytical solutions applied in respect of business problems/opportunities.
Undertake research into alternative data mining techniques and methodologies, with the objective of growing the knowledge base and discovering techniques and methodologies that may have a more practical business application.
Experiment and innovate by utilising alternative data mining techniques for analytical solutions that are required by business stakeholders, with the objective of achieving enhanced results.
Constantly strive to enhance the analytical solutions produced for business stakeholders by means of refreshing models and developing response models.
Accountability: Existing Customer Management (ECM) Support on Campaigns
Actively engage with ECM team to clarify campaign objectives and specifications whenever a request for an extraction of leads for a campaign is received.
Utilise the specifications received to analyse the volume of prospective customers in the Data Warehouse who match the criteria to provide an initial view of potential campaign volumes and potential financial impacts and forward on to the ECM team.
Extract the list of customers that will serve as leads for each campaign and apply the relevant business rules.
Adhere to the timelines and quality standards agreed to within the team and with clients.
Pro-actively manage uncertainty with requirements or criteria to be used to ensure campaign addresses identified challenges in the analytics phase.
Create control groups to benchmark success where required.
Ensure all campaigns are tracked either in own environment or MI environment.
Utilise outcome of ECM campaigns to refine and improve future campaigns.

Accountability: Adherence to Data Governance
Adhere to the core data governance disciplines as defined by the DGO (Data Governance Organisation), which includes data quality management, information life-cycle management and information security & privacy.
Perform integrity checks on all extracted data to ensure correct data is utilised in the analyses.
Escalate issues identified to the DGO.

Knowledge & Skills:

In-depth knowledge of analytics processes and methodologies
Solid understanding of data warehousing concepts, architectures, and processes
Deep understanding and experience in analytics domain
Understanding of the analytics solution market
Strong analytics skill set
Business domain knowledge
Team leadership skills
Presentation and Influencing skills
Strong Stakeholder Engagement
Competent Report Writing skills

Competencies:

Deciding and initiating action
Learning and researching
Entrepreneurial and commercial thinking
Relating and networking
Adapting and responding to change
Persuading and influencing
Creating and innovating
Presenting and Communicating Information
General
The appointment will be made in line with the Absa Employment Equity strategy

Essential/Basic Qualifications
A Bachelor’s degree in Statistics, or Data Science, (Applied, Pure or Industrial) Mathematics, or similar equivalent NQF level 7 or higher qualification
At least three (3) years’ experience as a business analyst
At least three (3) years advanced analytics experience
Proficient in MS Office (Word, Excel, PowerPoint and Outlook) and the Internet
No criminal record

Preferred requirements

Post Graduate Degree or equivalent NQF level 8 or higher qualification
Preference will be given to South African Citizens and Permanent residents of South Africa with proof of permanent resident status.

Apply Now

Source: Indeed

Previous articleCleaner or Tea Lady urgently needed: Apply Now
Next articleExternal Sales Consultant wanted: Salary R25 000 to R27 000 per month