Outlier detection has been and continues being one of the most important problems with wide applications in the domain of data mining. In online social networks such as Twitter, outlier detection methods can be used to detect bots; for sales and e-commerce companies, outlier detection can be used on the historical data in sales recording to detect malicious behaviors; for physical hosts in the World Wide Web, outlier detection can be used in the SMTP/HTTP transmission records to find out the potential attacks to them.

In this Kaggle competition, you are given a separate dataset, "conn250K.csv", which records the same data transmission history as described in the handout of Project 2. Your task is to run your implementation of outlier detection and report if each record in "conn250K.csv" is an attack or not.

*   Data: Description of the dataset is under the "Data" tab.
*   Evaluation: Description of the evaluation is under the "Evaluation" tab.
*   Timeline: **Deadline: Oct 27th, 5:00 pm**.


### Acknowledgments

This competition is a part of the Project 2 released in EECS 498 (Fall 2017): data mining from the University of Michigan, Ann Arbor.