Fill This Form To Receive Instant Help
Fill This Form To Receive Instant Help
Homework answers / question archive / Course Project Information security and machine learning Complete a data analytics project in Information security * The data analytics project stages will be distributed in the three milestones * The paper will talk also about the team data analytics project * You need to have a team from 1-3 students * The team should pick one of the datasets in discussion board and reserve it making sure that the dataset is not used by any other team Create an account in https
Course Project
Information security and machine learning
Complete a data analytics project in Information security
* The data analytics project stages will be distributed in the three
milestones
* The paper will talk also about the team data analytics project
* You need to have a team from 1-3 students
* The team should pick one of the datasets in discussion board and
reserve it making sure that the dataset is not used by any other team
Create an account in https./' /www.kaggle.corn
See my sample report for assignment I to be used as a rubric for this assignment. As I
demoed in the sample this dataset (https./' /www.kaggle.com/c/microsoft-malware-
prediction/kemels), exclude it also from your selection.
Go over the sections: Data, Kernels, Discussion, Activity to understand the data analytic
goals behind the dataset. Then summarize this in I -2 pages.
Download one of the following data analytic tools (or else use Python or Java
IDES/packages if you have programming skills):
will be given a grading advantage (as it requires more effort to program than to use
Guidelines for Grading/Assessment of Milestone 1
Each Milestone has roughly a third of overall project grades. Both milestone presentation and
report will contribute to the milestone grade.
The team will be assessed based on the overall progress up to the milestone. There are
minimum criteria (related to data science projects' tasks and also template components). In
addition, top 10-20 % will be assessed based on relative contribution/achievement among all
teams.
Report content should reflect what you have completed so far.
The final research report should follow research paper templates (You can see examples in
the following links: http://open.lib.umn.edu/writingforsuccess/chapter/13-I-formatting-a-
research-r/, https./' /style.mla.org/formatting-papers/,
http://www.aresearchguide.com/4format.html, https./' /explorable.com/research-paper-format,
https./' /owl.english.purdue.edu/owl/resource/560/18/,
https://www.ece.ucsb.edu/~parhami/rsrch paper dins.htm.
I will also upload samples of "anonymous good previous submissions" for your preference
You will submit in Milestone}: (I) Abstract, (2) Research Questions, (3) Introduction + ((4)
analysis progress: e.g. data collection, and preprocessing activities), with size of no less than
3 pages (standard times new roman 12 fonts 1.5 space)
Be prepared to present both your code progress as well as your report (Presentation is part of
the grade for both code and report).
|
For Milestones, you should prepare a power point presentation, but you will not be graded |
|
for the presentation part unless you present your work orally.
You have to evaluate all other students presentations according to the assessment form
template. Submit your assessment before you leave live session, Although your assessment to
others will not be impacting your grade, yet lacking to submit them will cause your own
presentation to be out of 70% instead. |
|
~~~~~~~~~~~~~~~~~~
Guidelines\Rubrics to deliver Project Report components
, . , . . . , . . . , . . . . . , . . . , . . . . , . . . . . , . . . , . . . , . . . . . , . . . , . . . , . . . . . , . . . , . . . , ~ , . . . , . . . ~ |
|
Deliverable 1 |
|
Guidelines\Rubrics to deliver Project Deliverable 2 and Final Deliverable
In deliverables 2 and final, you add the new sections in addition to any - Deliverable 2 components - |
|
(1)(Previous/Related Contribu6ons) (30 %) [ Kernel codes and also relevant literature}
As most of the selected projects use public datasets, no doubt there are different |
|
assessment |
|
Evaluating existing source codes that they have (e.g. in Kernels and discussion sections) In addition to the code, summarize most relevant literature or efforts to analyze the same If you have a new dataset with no or limited Kernel, survey literature not necessary
(2)Features Selec6on / Engineering (40 %)
(See this link for content of the next section)
We talked about feature selection methods and I uploaded several samples about that. I We suggest you provide: partial plots for the 3-5 most important features If this is not possible, you should provide a list of the most important features. How did you select features? Did you make any important feature transformations? Did you find any interesting interactions between features? Did you use external data? (if permitted)
Simple Features and Methods (Partial, part of the final grading)
Many customers are happy to trade off model performance for simplicity. With this in mind:
Is there a subset of features that would get 90-95% of your final performance? Which features?
What model that was most important? * What would the simplified model score?
* Try and restrict your simple model to fewer than 10 features and one training |
3)Training Method(s) (Par6al, part of the final grading) 30 %
Use the questions below to guide your effort in this section. (if you can answer all
questions with evidences/screenshots from your work, that is great)
What training methods did you use?
Did you ensemble the models?
If you did ensemble, how did you weight the different models?
A6. Interesting findings
What was the most important trick you used?
What do you think set you apart from others in the competition?
Did you find any interesting relationships in the data that don't fit in the sections above?
Model Execution Time (Partial, part of the final grading)
Many customers care about how long the winning models take to train and generate
predictions:
How long does it take to train your model?
How long does it take to generate predictions using your model?
How long does it take to train the simplified model (referenced in section A6)?
How long does it take to generate predictions from the simplified model?
Ensemble and Deep learning methods (Partial, part of the final grading)
We will cover ensemble, DL methods in the last two weeks. Details, quality and thoroughness
of evaluated Ensemble and DL methods are important factors in grading of the final
deliverable
References (Partial, part of the final grading)
Citations to references, websites, blog posts, and external sources of information where
appropriate.
Part of the final report
A comparison study
and analysis comparison not literature review)
Summary
Summarize the most important aspects of your model and analysis, such as:
The training method(s) you used (Convolutional Neural Network, XGBoost)
The most important features
The tool(s) you used
How long it takes to train your model
