1bm110 data analytics for business intelligence Practice exam and answers including calculations 100% CORRECT ANSWERS AID GRADE’A’

Instructions In this assignment, you will practice in implementing a document similarity task in a real world problem, namely question answering for online business customer support. The objective is to assess your understanding and skills in applying various pre-processing, text representation, text similarity and performance evaluation methods, select yourself the type of processes you apply, and critically reflect and justify the choices you made. • Use KNIME or Python for your implementation. • Explain your code using comments. Work together with your group mates. You may also discuss and share ideas with others, however, do not submit anything that is not your own group work and make sure you acknowledge and cite properly the work of others. Try to be concise but do provide a justification or an explanation where applicable. The page limit for your report is 4 pages, i.e. one page for discussing each of the four implementation steps including any tables or plots. For any questions, clarifications and hints: it is highly recommended that you attend the Q&A sessions on Fridays. Alternatively you may use the CANVAS Discussions. Deliverables 1. Your document similarity task implementation in *.py file format (using Python or KNIME), as spec- ified in question 1. 2. A report discussing your implementation in *.pdf format, as specified in more detail in question 2. Both these files should be compressed into a single *.zip archive for submission. Submission • Deadline: March 29th, 2021. • File names for your deliverables: – Group[GroupNumber]A (e.g. Group01A, if you are group 1). – Group[GroupNumber]A (e.g. Group01A, if you are group 1). – Deliverables compressed in a single zip archive named Group[GroupNumbe