Week4

docx

School

Tidewater Community College *

*We aren’t endorsed by this school

Course

100

Subject

Information Systems

Date

Feb 20, 2024

Type

docx

Pages

Uploaded by AgentNeutron7333

Levi Banks MACHINE LEARNING SYSTEMS AND DATA ANALYTICS IN CYBERSECURITY

When discussing machine learning it is usually in reference to the field of artificial intelligence whereas analytical model building is automated. This is done with minimal human intervention. Using data that has been put into the system, allows the system to learn the patterns, or trends per se, and make decisions based on these trends. Although machine learning is fairly new it’s very important to technology as it is able to adapt to new data produced in different forms, enabling companies to make informed decisions. With more data, and different types of data being used each day, machine learning can be advantageous to companies producing models that will deliver faster, accurate results based on complex data. The key concepts that are required for a good machine learning system are, scalability, algorithms, automation and iterative processes, data preparation capabilities and ensemble modeling. With that being said, we will discuss some key elements of machine learning, types of learning and how it ties in with the concepts of data analytics. With hundreds of new algorithms being developed each learning algorithm has three components. Representation, Evaluation and Optimization. Representation details how the information should be represented, whether it’s instances, decision trees, or model ensembles, etc. Evaluation is basically how the data is evaluated, this could be evaluated for speed, accuracy, likelihood, probability and more. And Optimization is the way that the programs are generated. Types of machine learning algorithms are supervised, semi-supervised, unsupervised, and reinforcement (Artificial Intelligence,2021). With supervised learning a known dataset with the desired inputs and outputs are provided and the algorithm has to figure out how to arrive at those results. Using patterns or trends the algorithm makes predictions, which is then corrected by the operator, and this process continues until the highest level of accuracy is reached. Withing

supervised learning there are three tasks, classification in which a conclusion is drawn from the observation of values too show what category the new observation belongs, regression tasks where an estimation is done by the machine learning program, and forecasting tasks where predictions are made based on past and present data. Semi-supervised learning the machine learning algorithm is fed labeled and unlabeled data giving the learning system the ability to label the unlabeled data. Unsupervised learning is when the algorithm identifies trends by studying and analyzing the data, and arranging into clustering, grouping similar data, or dimension reduction, in which the number of variables are reduced. Reinforcement learning involves providing the algorithm with a set of actions, parameters, and end values. With this information being fed to the machine learning algorithm, it evaluates various options and possibilities, monitoring each to determine which one is adequate. Data Analytics, which involves sorting through massive amounts of data, goes through a process to determine what the data is trying to tell you. You must first have an idea of what you want to learn from the analysis, collect the correct data, ridding it of unnecessary data, or mistakes, manipulating data using software applications, and then presenting the results visually via charts, graphs, tables…etc. Being as machine learning is a newer, more advanced technology when it comes to the accuracy of gathering and presenting data, it fares better than regular data analytics. Data analytics is more operator involved, where as the machine learning basically automates the process by learning the data and automating the results.

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Applying machine learning and data analytics to the field of cybersecurity would help the security analyst sort through the large amount of raw data that it captures from day- to-day. Using data analytics to visually display this data and present it to executive leaders allows the company to be more efficient and affective in finding issues and rectify them. Machine learning systems takes that a step further, by automating the procedure, the security analyst does not have to worry about finding as many qualified candidates to repudiate important systems. With machine learning systems, if a network has been penetrated and there is a need to pinpoint exactly what information was compromised, how it was compromised and what needs to be done to repair the issue, the answer can be easier to discover, and more quickly repaired based on patterns and the machine learning system providing accurate information to fix it. Some of the companies that provide innovative defensive cybersecurity measures based on these technologies include, CrowdStrike, Darktrace, SAP NS2, and Webroot. While all these companies are excellent in providing ML and data analytics to discover and understand cybersecurity attacks, the companies that I would recommend to the CTO, are SAP NS2, for its “use of AI and ML technology to help national security professionals process troves of data and protect sensitive information passing through a variety of locales. (Greig, 2020)” SAP NS2 also secures supply chains, which involve many vendors and inventory tracking. But also, because it uses AI and ML to protect cloud platforms, which any companies are migrating to. CrowdStrike is another company would recommend, partly due to their popularity in the market but also because their use of machine learning offers quicker visibility and protections across the organization and focuses on prevention, thus being pro-active as opposed to reactive in thwarting attacks.

Works Cited Artificial Intelligence vs machine learning VS data analytics: What you need to know? Artificial Intelligence, Big Data Analytics, and Insight. (2021, August 6). Retrieved September 17, 2021, from https://www.analyticsinsight.net/artificial-intelligence-vs- machine-learning-vs-data-analytics-what-you-need-to-know/. Greig, J. (2020, March 2). Eight leading AI/ML cybersecurity companies in 2020 . ZDNet. Retrieved September 17, 2021, from https://www.zdnet.com/article/eight-leading-aiml- cybersecurity-companies-in-2020/. A guide to the types of machine learning algorithms . A guide to the types of machine learning algorithms | SAS UK. (n.d.). Retrieved September 17, 2021, from https://www.sas.com/en_gb/insights/articles/analytics/machine-learning-algorithms.html. -

Week4

Related Documents