Question

You have been hired as a security and data analyst for a company operating an online social media platforman. You are tasked to work on a project to identify possible threats related to fake user accounts (so called sibyls ). How can you get started on the project? Try to break it down using the the six phases of the CRISP-DM process. Start your analysis by explaining briefly what the goal of each phase of CRISP-DM is. Use bullet structured lists and short sentences to stucture your response. Do not write paragraphs of prose text.

Answer 1

FOR THE CURRENT MY SET OF 6 CRISP DM STEPS WOULD BE

1)UNDERSTANDING THE BUSINESS.

• consider the intended outputs of the project(identify possible threats)
• analyse objectives,calculate cost,resources needed.(the number of data analysts,data required,manpower and other costs required to handle the problem
• reliable source of data.(try to gather data from previous records of such incidences)
• adress the given problem with a viable solution.( develop a method to quickly identiify fake accounts an mitigate the threat)

2)UNDERSTANDING THE DATA

• Outline data requirements.(during data collection the data should be focussed on fake accounts related records)
• Verify data availability.(if there has been no data available,pretest data using the possible simulations of fake accounts)
• gather data from about behavior of fake accounts
• study the problems created by the fake accounts
• Define selection criteria(if data is available,try to prioritize data regarding specific threats/significant threats from fake accounts)
• obtain data.(can be done through user feedback,crash reports,server records,or outsourced dat from a data collection agency)
• explore data(examine the data throughly to analyze the situation)
• verify data quality.(select the important bits?relevant data to be taken to consideration)

3)PREPARATION OF DATA

• identify any patterns in data

• Selecting data(as explained earlier look for signifant data in the system)

• Cleaning data.(for ease of problem solving)

• Constructing data.(data should be organised to be studied properly)

• Integrating data

• Formatting data

4)MODELING

• selecting modelling techniques(as per requirement)
• designing tests(testing the project)
• building models
• assessing models

5)EVALUATION

• evaluating process(check if the required problem has been solved)
• reviewng process.(determine if the project has obtained the objectives)
• determining next steps.(either proceeding with the project or employing corrective measuress)

6)DEPLOYMENT

• planning deployment methods.(through application updates/hardware/security based upgrade)
• planning and monitoring perfomance.(check for user inputs and mock breakins to test the feature)

----------------------------------------fin-----------------------------------

• reporting final results.(collect the final data)
• revieving final results.(evaluate the results)