Scribd
Upload
3 views2 pages

Predictive Analytics

Diploma Exam Past Paper. Ict Department Zetech University, Nairobi Kenya. Data Science, Data Analytics.

Uploaded by

joanami
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
3 views2 pages

Predictive Analytics

Diploma Exam Past Paper. Ict Department Zetech University, Nairobi Kenya. Data Science, Data Analytics.

Uploaded by

joanami
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
ZETECH UNIVERSITY Inventing the future ZUNWI/7/EXM/6 UNIVERSITY EXAMINATION 2025/2026 ORDINARY EXAMINATION FOR THE DIPLOMA IN DATA SCIENCE AND ANALYTICS DSA 212: PREDICTIVE ANALYTICS PI INSTRUCTIONS: ANSWER QUESTION ONE AND ANY OTHER TWO QUESTION ONE [50 Marks] a) Define predictive analytics and explain its importance in decision making. (4 marks) b) b) A retail company wants to predict whether a customer will retum to make another purchase. Identify the type of predictive model suitable for this task and justify your answer. (4 marks) ¢) Explain the difference between classification, regression, and clustering using one example for each. (6 marks) @) Describe feature selection and explain why it is important when building predictive models. (S marks) €) Explain the concept of statistical computing in predictive analytics. (S marks) f) Describe THREE limitations of predictive models in real-world applications. (6 marks) QUESTION TWO [15 Marks] A university wants to predict student performance using study habits data. a) Identify THREE possible predictor variables that can be used in this model. ( marks) b) Explain THREE feature selection techniques that could be applied to select important predictors. (6 marks) ©) Describe TWO challenges that may arise when using too many predictors. (4 marks) 4) Explain why feature selection improves model performance. (2 marks) 1[Pageo QUESTION THREE [15 Marks] @) Dofine cross-validation. {2 marks) b) Explain how k-fold cross-validation works. (5 marks) ¢) Doscribe TWO benefits of using cross-validation when evaluating predictive models. (4 marks) d) Explain TWO limitations of cross-validation. (4 marks) QUESTION FOUR [15 Marks} A bank wants to group customers based on spending behaviour. a) Identify the type of predictive medelling technique suitable for this task. (3 marks} b)_ Explain how unsupervised learning differs from supervised learning. (4 marks) ©) Describe the application of random forest in predictive analytics. (4. marks) d) Explain why predictive analytics is useful in business strategic decision making. (4: marks) 2|Page

You might also like