Data-driven decision support

Data-driven decision support encompasses a range of the most essential processes of data
analytics, including data preparation and integration, modelling using statistical and/or
machine learning techniques, and data presentation. The aim of this activity is to empower
the organisational decision-making with statistically tested and systematically evaluated
decision options. These options can be ranked using inferential models, such as forecasting,
prediction and/or classification.
In Part 1 of this assignment, you have identified a case study – an organisation or project of
your choice, as well as various data sources and datasets available to it, and an important
organisational decision. In this part, you have an opportunity to demonstrate how this
specific decision formulated in Part 1 in the context of your chosen case study can be
supported with data analytics.
Task 2.1
Discuss data preparation process, including
• Explanation of data collection, filtering and integration procedures.
• Analysis of data representativeness.
• Statement on generalisability and limitations of the integrated dataset.
(800 words)
(20 marks)
(LO 2)
Task 2.2
Perform data modelling, which should specifically demonstrate:
• Selection and justification of the inferential and/or machine learning models, most
relevant to the objectives of your case study.
• Application of statistical tools such as Excel, SPSS and/or Weka, to your model and
reporting on the initial outcomes of your modelling.
• Explanation what the decision in question should be, based on these outcomes.