Enrollment Predictions with Machine Learning

Happy to announce that our joint paper, Enrollment Predictions with Machine Learning, co-authored with Hung Dang, Ginger Reyes Reilly and Katharine Soltys, has appeared in Volume 9, number 2, of the Strategic Enrollment Management Quarterly (SEMQ).

In this paper a Machine Learning framework for predicting enrollment is proposed. The framework consists of Amazon Web Services SageMaker together with standard Python tools for Data Analytics, including Pandas, NumPy, MatPlotLib and Scikit-Learn. The tools are deployed with Jupyter Notebooks running on AWS SageMaker. Based on three years of enrollment history, a model is built to compute — individually or in batch mode — probabilities of enrollments for given applicants. These probabilities can then be used during the admission period to target undecided students. The audience for this paper is both SEM practitioners and technical practitioners in the area of data analytics. Through reading this paper, enrollment management professionals will be able to understand what goes into the preparation of Machine Learning model to help with predicting admission rates. Technical experts, on the other hand, will gain a blue-print for what is required from them.

This paper has been made possible in part by the AWS Pilot Program in Machine Learning where California State University Channel Islands was one if the participating institutions.

Sarah Hassan at Apple

Sarah Hassan is a 2021 graduate with a BS in Computer Science and a minor in both Visual Media Communication and Mathematics. During her years at CSUCI, Sarah was working part-time at her local Apple Store as a Technical Specialist. While working at Apple and being a fresh graduate, she was granted the opportunity to partake in what is known as a Career Experience, an opportunity for employees to experience a new role while contributing to important projects at Apple. Her role is a Siri Experience Prototyper in the Siri Conversational Interaction team. Sarah believes that her Capstone project (an iOS application) was able to leave a good impression during her interviews along with her graphic design knowledge. She was able to share her link to her Capstone project and discuss technical/design challenges she’s faced while also sharing graphic design work she has done at CSUCI.

Computer Science 8th Advisory Board Meeting

Previous Advisory Board Meeting (7th)

most Important: CaPstone Showcase

Please help us make our students’ Virtual Capstone Showcase a special occasion by visiting the sites of their projects, and leaving a comment. Our students have worked hard to meet the demands of a senior capstone project, in difficult circumstances, and they are facing a challenging job market (although Computer Science is doing relatively well even in the COVID19 economy). It will encourage them to have your feedback, as industry leaders.

Here is the list of all the Capstone projects:

  1. csuci.joseph-cherry.com
  2. capstone.kyliegodi.cikeys.com
  3. newsol.cikeys.com/Capstone
  4. michaelcurry.cikeys.com/pandemic-simulator
  5.  dcsrichardzins.cikeys.com
  6. jonathanginsburg128.cikeys.com
  7. sarahhassan.cikeys.com
  8. robertocasas.cikeys.com
  9. studypal.cikeys.com
  10. aaronjimenez.cikeys.com
  11. capstone.bernadetteplaisted.cikeys.com
  12. chromatic.birdbuddy.cikeys.com
  13. truesoria.cikeys.com/beastmode
  14. royceshropshire.cikeys.com
  15. mattbrierley.cikeys.com
  16. arthurdevsite.cikeys.com
  17. rlorelli.cikeys.com/project-showcase
  18. captureball.com/overview
  19. twalsh.cikeys.com
  20. nicholascaballero363.cikeys.com/OneStepAtATime
  21. jgottlieb.cikeys.com/uncategorized/joshua-gottlieb-spring-2021-capstone
  22. angelayqiao.cikeys.com
  23. capstone.freddie.daada.cikeys.com/blog/
  24. capstone.yarelit.cikeys.com/
  25. www.wordpress.cikeys.com/home
  26. securesecurity.cikeys.com
  27. austinfisher.cikeys.com/Portfolio-Pal
  28. neil-marcellini.cikeys.com/capstone
  29. joserodriguezrivas.cikeys.com
  30. competdium.cikeys.com
  31. gavinsingh.cikeys.com
  32. williamkempema.cikeys.com/Capstone
  33. meerathierumaran903.cikeys.com/home
  34. alnavarro.cikeys.com/capstone
  35. seanblanch.cikeys.com
  36. shahrdadshadrou-journey.cikeys.com
  37. trurob.cikeys.com/blog
  38. dinoswars.cikeys.com
  39. jsteelsmith.cikeys.com/project-page
  40. zhiliwangcapstone499.cikeys.com
  41. cardenkidsacademypreschool.cikeys.com

Summary of the Meeting

  1. Enrollment challenges: a dip of about 50% in CS, IT and Mechatronics Engineering students.
  2. Philanthropic success: SCE, HAAS, B. Johnson and Meissner Filtration gifts. We are very grateful!
  3. Faculty write papers, participate in conference and events, write grants.
  4. AWS first year of certificate: we are very happy with hosting so many programmers and software engineers in our classes.



Tips for educators to master virtual instruction | AWS Public Sector Blog

As educators, we need to approach the transition to online teaching as permanent change and innovate for the future. At California State University, we have moved to virtual instruction repeatedly throughout the last five years for a variety of reasons. I encourage educators to have an online version for all your classes, not only for emergencies, but also to be responsive to students who want online offerings.

In this AWS Public Sector Blog post I discuss how to:

  1. Leverage technology to replace face-to-face interaction.
  2. Make the tech work for you.
  3. Get creative.
  4. Throw out the rulebook.
  5. Change the way you approach grading.
  6. Balance organization with passion.
  7. Bonus tip for computer science instructors: Some material is easier to teach online.

From: https://aws.amazon.com/blogs/publicsector/tips-for-educators-to-master-virtual-instruction/

KVTA 1590 Interview on the AWS Cloud at CSUCI

Interview on the partnership between CSUCI and Amazon Web Services, Dec 7, 2020

Main Points of the interview:

  1. Can you explain what a“cloud” is for the laypeople?
    • In some sense it is giant warehouses filled with computers
    • But more importantly it is a new paradigm of computing, described often as on demand access to IT resources via the Internet with a pay-as-you-go plan
    • A good analogy is the power grid; instead of running your own generator, and its backup, and being responsible for its maintenance and operation, you connect to the grid, and outsource those responsibilities to the power company. Then you are just responsible for paying the bills. 
  2. Give a short history of the Cloud.
    • Started over a 100 years ago with the telegraph, smart terminal and operator at the edges, but “dumb” inside (just a cable and repeaters)
    • Then the telephone, dumb at the edges, but smart inside with the switchboard / circuit switching
    • Then the Internet, again flipping the paradigm, smart at the edges, dumb inside – 50 years ago
    • Finally the cloud, going back to the original, dumb at the edges, smart inside – 15 year ago
  3. How is Artificial Intelligence, in particular Machine Learning, connected to the Cloud?
    • Machine Learning is a method of computing where the computation is data driven, rather than instruction driven. A good example, is Optical Character Recognition – you can train the computer to recognize hand written digits, e.g., depositing a check the OCR software extracts the amount from the check.
    • The mathematical idea behind it is a perceptron, that models the neurons in the human brain, and this was first discovered in the 1960s but at that time we lacked the computer power to implement it in practice.
    • Suddenly, 15 years ago or so with the advent of the data center, more companies and institutions had access to the necessary computer power.
    • But since 5 years, maybe a little longer, individuals have access to it via the Cloud. Our AWS Pilot in Machine Learning – students have access to the latest.
  4. What are some examples of the Cloud?
    • Service that we all use: Dropbox, Netflix, Gmail, etc.
    • Your handheld device does not have a lot of compute power, so in some sense it is a portal into the cloud – google maps directions are computed for you in the cloud
  5. Is the cloud secure?
    • That is a very good question, but it does not have a yes/no answer. Security is assessed with risks and probabilities.
    • But, in general, a company like Dropbox has tremendous resources and expertise at its disposal to secure your data.
    • On the other hand, how secure is your data in on-premises solution? 
    • In any case, businesses are moving swiftly into the cloud, because the pricing is so attractive, but their number one concern is: will my data be secure? 
    • Famous saying of Gene Spafford: “The only truly secure system is one that is powered off, cast in a block of concrete and sealed in a lead-lined room with armed guards – and even then I have my doubts.
  6. What is the job market in the cloud?
    • Excellent, LinkedIn has listed cloud skill as the #1 skill searched for by employers since 2014.
    • That is why we have been growing our Cloud offering at CSUCI. 

How can I learn more about the cloud

  1. List of certification classes
  2. Link to sign up

Computer Science 7th Advisory Board Meeting

most Important: CaPstone Showcase

Please help us make our students’ Virtual Capstone Showcase a special occasion by visiting the sites of their projects, and leaving a comment. Our students have worked hard to meet the demands of a senior capstone project, in difficult circumstances, and they are facing a challenging job market (although Computer Science is doing relatively well even in the COVID19 economy). It will encourage them to have your feedback, as industry leaders.

Here is the list of all the Capstone projects:

  1. http://marcusit308.cikeys.com/
  2. http://translator.cikeys.com/
  3. https://www.retropi.capstone.justindelgado001.cikeys.com/blog/
  4. http://kirstyalexandranguegang.cikeys.com/
  5. http://abdulnachawati.cikeys.com/
  6. http://polyrhythmmetronome.cikeys.com/
  7. http://www.capstone.luisfigueroa.cikeys.com/
  8. http://thomasmadsen.cikeys.com/
  9. http://jasondiep.cikeys.com/
  10. http://zacharylloyd.cikeys.com/capstone/
  11. http://roguespaceproject.cikeys.com/project-page/
  12. http://adam.cikeys.com
  13. http://connorstephens.cikeys.com/uncategorized/final-capstone-submission/
  14. http://cross.cikeys.com/capstone/uncategorized/final-project/
  15. http://www.isaac-garza.icheadache.cikeys.com/
  16. http://csuci-nibbe.cikeys.com/
  17. http://brettmusser.cikeys.com/
  18. http://elliottdiaz.cikeys.com/

Summary of the Meeting

  1. Introduction to the Computer Science Advisory Board meeting, Chris Meissner
  2. 10min + questions: term overview and updates by Michael Soltys (see slides below)
  3. 15min + questions: update on Mechatronics by new faculty Bahareh Abbasi and Vida Vakilian (see slides below)




Cloud Computing certification training open to the public at CSUCI

This year I am teaching (online) a sequence of 4 courses in Cloud Computing, in conjunction with the AWS Academy. Students receive AWS accounts, explore AWS services with hands-on labs, and prepare for certification (if they wish to). All classes are open to the public, and can be joined independently of each other (or all taken in sequence!). Please contact jeff.ziskin@csuci.edu to book an information session meeting on Zoom.

Computer Science selected for an AWS Pilot program in Machine Learning

We are very happy to have been selected for an SageMaker Pilot for AWS Educate Classrooms! Machine Learning (ML) is a top hard skill for graduates, and it is also becoming a premier tool for research in all areas. SageMaker Studio is a complete development environment for ML.

The theory of ML can always be taught, but in order to have hands on experience with ML, a computing infrastructure is required that is beyond the means of most educational institutions. Our students will have access to AWS Educate accounts with credits to use the SageMaker Studio environment, and access to to powerful CPU/GPU resources (ml.m5.xlarge, ml.c5.xlarge, and ml.g4dn.xlarge) for training ML models.

ML use cases include SPAM filtering for emails, recommender systems, e.g., Netflix show recommendations, and uncovering credit card fraud. There are three types of ML: supervised, where the data is labeled and the expected outputs are well understood (is an, is this email SPAM or not); unsupervised, where the ML algorithm has to discover the salient properties of the data; and, reinforcement, where some agent (e.g., RoboMaker) interacts with an environment and learns to navigate it through a system of rewards.

SageMaker supports many leading deep learning frameworks, including: TensorFlow, PyTorch, Apache MXNet, Chainer, Keras, Gluon, Horovod, Scikit-learn, and Deep Graph Library.

We applied last July to be part of the AWS pilot program to make SageMaker available to our students, and we were approved to start this fall 2020. We have a group of about 10 students who are going to be learning to use under my supervision.

We are building on our growing expertise in Artificial Intelligence. This fall term, professor Reza Abdolee is teaching a graduate class in AI (COMP569) and professor Bahareh Abbasi is teaching both an undergraduate course in AI (COMP469) and a graduate class in Neural Networks (COMP572).

ML is one of the areas of AWS certification.

Students will learn a variety of auxiliary tools; as you will see from this list, the Python programming language is central to Data Analytics:

  • Jupyter Notebook and Jupyter Lab: an open-source web application that allows the creation and sharing of documents that contain live code, equations, visualizations and narrative text. Uses include: data cleaning and transformation, numerical simulation, statistical modeling, data visualization, machine learning, etc.
  • Pandas: a software library written for the Python programming language for data manipulation and analysis. In particular, it offers data structures and operations for manipulating numerical tables and time series.
  • Seaborn: a library for making statistical graphics in Python. It is built on top of Matplotlib and closely integrated with Pandas data structures.
  • Scikit-learn: a free software machine learning library for the Python programming language. It features various classification, regression and clustering algorithms.
  • Matplotlib: a comprehensive library for creating static, animated, and interactive visualizations in Python.
  • NumPy: a library for the Python programming language, adding support for large, multi-dimensional arrays and matrices, along with a large collection of high-level mathematical functions to operate on these arrays.
  • PyTorch (AWS testimonials): an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Facebook’s AI Research lab.

In the words of Jose Cahue:

One of the major hurdles to learn ML as a student is having access to a machine optimized for model training. Cloud computing can be one practical solution to provide the computation resources needed to learn ML.

Jose Cahue

CI master students’ research accepted at the KES2020 international conference in Verona

KES 2020 in Verona but virtual

CSUCI Master of Computer Science students were successful in submitting two papers to KES 2020, the 24rd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems, which this year is taking place in Verona, Italy, in September 2020. However, due to the COVID pandemic, the conference will be held virtually. The papers are the following:

  • Malware Persistence Mechanisms, co-authored by Zane Gittins and Michael Soltys. Zane Gittins is a masters student in Computer Science at CSUCI, and this paper is the result of his masters thesis. Zane Gittins has worked as a Cybersecurity experts at HAAS, and currently is working at Meissner Filtration. (This paper will be presented in the General Track session G3b: Cybersecurity.)
  • Voyager: Tracking with a Click, co-authored by Samuel Decanio, Kimo Hildreth and Michael Soltys. Sam Decanio is a masters student in Computer Science at CSUCI, and this paper is the result of his masters thesis and a fruitful collaboration between Computer Science at CI and the SoCal High Technology Task Force. Sam Decanio is currently working at the Navy. (This paper will be presented in the General Track session G3b: Cybersecurity.)