Modern Data Science Assignment: A Data Analytic Small Project
This is a small project where students will be expected to work in teams of two. Students are required to submit a report that comprises data collection, data analysis and programming tasks. Assignment is based on topics presented. Although students will work in teams, each student must write a report independently and also the report will be assessedindividually.
The Data Analytic Small Project
Participants: A team of two students: both will finish the project together but write reports independently while sharing some parts of the reports if both contribute equally.
Project Description:
Select one from three topics introduced in Weeks 4-6:
(1) Common PatternDiscovery
(2) OutlierDetection
(3) Recommendation
and analyse one of the three types of data introduced in Weeks 7-9:
(a) timeseries
(b) shorttext
(c) trajectories
We list some examples: "Outlier detection from stock/sensor time series", "Product/movie/book comment (short text) analysis for recommendation", "Discovering common travel patterns from GPS trajectories for behavior analysis". But your own topics are not limited tothese.
Requirements:
(1) you need to collect data from the internet by yourselves. For example, you can download from open data sites or gather (crawl, integrate and prepare) them byyourselves.
(2) you need to focus on applying one data analytic algorithm, such as those that you have practiced in Practical (K-means, PCA and SVM) or others you learn by yourselves, to implement a small program to satisfy thisproject.
(3) you need to write a report (around 3-4 pages, Maximum 1500 words) about your discovery and the whole process of data collection and analysis, including the followingparts:
Project Title
Executive Summary
Data and Application Background (including how to collect and prepare data, what is the data size, what is the data type, what is the content in the data, what is the purpose (application scenario) of data analysis)
Data Analysis (describe how you use one classical data mining algorithm, such as K-means, PCA, SVM and others, to do data analysis and satisfy your application goal)
Results and Demonstration (show the results you have discovered and discuss the performance of your data analysis in terms of efficiency or accuracy etc)
Conclusion.
Attachment:- Assignment-Sample-Python-Codes.rar