Reference no: EM133069282
DATA4400 Data-driven Decision Making and Forecasting - Kaplan Business School
Assessment - Interpreting Forecasting based analytics
Assessment Task
Given an example of a web-based comprehensive forecasting application with multiple methods, provide a description and interpretation of the techniques used. The report is worth 30 marks (see rubric for allocation of these marks).
Description
A shiny web app. has been built to forecast monthly data using different methodologies. The application allows you to divide the data set between train and test set, so you can evaluate the performance of the models. You can use the error metrics provided to evaluate the performance and accuracy of the model.
A dataset will be provided to you at beginning of week 9. The objective of the assessment is to develop different forecast models in terms of accuracy, trend, and seasonality alignment with the historical data provided. Students must calculate the Root Mean Square Error (RMSE) or Mean Absolute percentage Error (MAPE) on the test data to provide conclusions and construct a dashboard in a BI tool.
Assessment Instructions
Report Structure and Content
1. Analyse the results of the forecast methodologies used, in terms of:
a. Accuracy
b. Alignment with the historical trend
c. Alignment with the historical seasonality
2. Use a BI tool and Exploratory.io to visualise the dataset and generate a forecast. Compare the forecast generated by the BI tool/Exploratory with the three forecasts generated by the Shiny app. Provide visualisations and describe your findings.
3. Recommend improvements to the shiny app.
4. Summary
Attachment:- Interpreting Forecasting based analytics.rar