Assessment 3 Assessment Type: Knowledge based Schemes - group project Purpose: Students will be working in a group of 4 students. Each student is required to work towards this project. This assessment is designed to reinforce the foundation theories taught and develop students' skills and application of knowledge of the subject content to provide useful insights for businesses. This assessment relates to learning Outcomes a, b, c and d. Value: 25% (Report 20%, Group Work Activity 5%) Due Date: Week 12 Assessment topic: Knowledge-based Schemes- Submission: Rapid miner file (rpm): Final report (.doc, docx) Week 12 Submit on Moodle. Task Details: You as a data scientist have been hired by a company to help the managers in extracting hidden knowledge from datasets. The hidden knowledge should reveal interesting information that helps the business to grow. For example, use of sentiment analysis/association rules/prediction models/clustering techniques can take advantage of Al to develop the business Key Performance Indicator (KPI). You may also work on some benchmark dataset related to health or incidents i.e., Titanic dataset. ICT371 Students will create a process in Rapid Miner generating knowledge from a dataset that will be uploaded on Moodle. The dataset will include numbers, text, and other labels. You may use different techniques such as sentiment analysis, association rules, ANN, DT, FT, K-means, SOM, and etc to produce insights about the dataset and conclude with useful advice about the business. Students need to use different visualization techniques to analyse and show the space of the problem. Students are expected to implement a minimum of 4 techniques. Beside the report, students should upload a single process file that includes all the 4 techniques, with a name of the form (StudentID] Knowledge.rmp. Assessment 3 Assessment Type: Knowledge based Schemes - group project Purpose: Students will be working in a group of 4 students. Each student is required to work towards this project. This assessment is designed to reinforce the foundation theories taught and develop students' skills and application of knowledge of the subject content to provide useful insights for businesses. This assessment relates to learning Outcomes a, b, c and d. Value: 25% (Report 20%, Group Work Activity 5%) Due Date: Week 12 Assessment topic: Knowledge-based Schemes- Submission: Rapid miner file (rpm): Final report (.doc, docx) Week 12 Submit on Moodle. Task Details: You as a data scientist have been hired by a company to help the managers in extracting hidden knowledge from datasets. The hidden knowledge should reveal interesting information that helps the business to grow. For example, use of sentiment analysis/association rules/prediction models/clustering techniques can take advantage of Al to develop the business Key Performance Indicator (KPI). You may also work on some benchmark dataset related to health or incidents i.e., Titanic dataset. ICT371 Students will create a process in Rapid Miner generating knowledge from a dataset that will be uploaded on Moodle. The dataset will include numbers, text, and other labels. You may use different techniques such as sentiment analysis, association rules, ANN, DT, FT, K-means, SOM, and etc to produce insights about the dataset and conclude with useful advice about the business. Students need to use different visualization techniques to analyse and show the space of the problem. Students are expected to implement a minimum of 4 techniques. Beside the report, students should upload a single process file that includes all the 4 techniques, with a name of the form (StudentID] Knowledge.rmp
