A Beginner’s Guide to Machine Learning

Mobile Phone Displaying a Graph

By Kirubakumaresh Rajendran

Ever wonder how apps, websites, and machines seem to be able to predict the future? Like how Amazon knows what your next purchase may be, or how self-driving cars can safely navigate a complex road situation?

The answer lies in machine learning.

Machine learning is a branch of artificial intelligence (AI) that concentrates on building systems that can learn from and make decisions based on data. Instead of explicitly programming the machine to solve the problem, we show it how it was solved in the past and the machine learns the key steps that are required to do the same task on its own from the examples.

Think about how Netflix makes movie recommendations. The recommendation engine peeks at the movies you’ve viewed/rated in the past. It then starts to learn the factors that influence your movie preferences and stores them in a database. It could be as simple as noting that you prefer to watch “comedy movies released after 2005 featuring Adam Sandler.” It then starts recommending similar movies that you haven’t watched — all without writing any explicit rules!

This is the power of machine learning.

Machine learning is revolutionizing every industry by bringing greater value to companies’ years of saved data. Leveraging machine learning enables organizations to make more precise decisions instead of following intuition. Companies have begun to embrace the power of machine learning and revise their strategies in order to remain more competitive.

Data Scientists: The Forces Behind Machine Learning

Machine learning is typically practiced by data scientists, who help organizations discover hidden value from their data — thereby enabling them to make smarter business decisions. For instance, insurers use machine learning to make accurate predictions on fraudulent claims, rather than relying on traditional analysis or human judgement. This has a significant impact that can result in lower costs and higher revenue for businesses. Data scientists work with various stakeholders in a company, like business users or product owners, to discover problems and gather data that will be used to solve them.

Data scientists collect, process, clean up, and verify the integrity of data. They apply their engineering, modeling, and statistical skills to build end-to-end machine learning systems. They constantly monitor the performance of those systems and make improvements wherever possible. Often, they need to communicate to non-technical audiences — including stakeholders across the company — in a compelling way to highlight the business impact and opportunity. At the end of the day, those stakeholders have to act on and possibly make far-reaching decisions based on the data scientist's’ findings.

Above all, data scientists need to be creative and avid problem-solvers. Possessing this combination of skills makes them a rare breed — so it’s no wonder they’re highly sought after by companies across many industries, such as health care, retail, manufacturing, and technology.

Supervised Learning

Machine learning algorithms fall into two categories, supervised and unsupervised learning. Supervised learning tries to predict a future value by relying on training from past data. For instance, Netflix’s movie-recommendation engine is most likely supervised. It uses a user’s past movie ratings as training data to the model and then predicts your rating for unseen movies. Supervised learning enjoys more commercial success than unsupervised learning. Some of the popular use cases include fraud detection, image recognition, credit scoring, product recommendation, and malfunction prediction.

Unsupervised Learning

Unsupervised learning is not about prediction but rather about uncovering hidden structures from the data. It’s helpful in identifying segments or groups, especially when there is no prior information available about those segments. These algorithms are commonly used in market segmentation. They enable marketers to identify target segments in order to maximize revenue, create anomaly detection systems to identify suspicious user behavior, and more.

For instance, Netflix may know how many customers it has, but wants to understand what kind of groupings they fall into in order to offer services targeted to them. The streaming service may have 50 or more different customer types, aka segments, but its data scientists don’t know yet.

If the company knows that most of its customers are in the “families with children” segment, it can invest in building specific programs to meet customer needs. But without that information, Netflix’s data scientists can’t build a supervised machine learning system. So, they build an unsupervised machine learning algorithm instead, which identifies and extracts various customer segments within the data and allows them to identify groups such as “families with children” or “working professionals.”

Machine Learning at General Assembly

At General Assembly, our Data Science Immersive program trains students in machine learning, programming, data visualization, and other skills needed to become a job-ready data scientist. Students learn the hands-on languages and techniques, like SQL, Python, and UNIX, that are needed to gather and organize data, build predictive models, create data visualizations, and tackle real-world projects. In class, students work on data science labs, compete on the data science platform Kaggle, and complete a capstone project to showcase their data science skills. They also gain access to career coaching, job-readiness training, and networking opportunities.

If you’re looking to learn during evenings and weekends, you can explore our part-time Data Science course, or visit one of GA’s worldwide campuses for a short-form event or workshop led by local professionals in the field.

Meet Our Expert

Kirubakumaresh Rajendran is an experienced data scientist who’s passionate about applying machine learning and statistical modeling techniques to the domain of business problems. He has worked with IBM and Morgan Stanley to build data-driven products that leverage machine learning techniques. He is a co-instructor for the Data Science Immersive course at GA’s Sydney campus, and enjoys teaching, mentoring, and guiding aspiring data scientists.

“Machines are helping humans build self-driving cars, cancer detection, and more, making it the right time to roll up your sleeves, get into the world of machine learning, and teach machines to make the world a better place.”

Kirubakumaresh Rajendran, Data Science Immersive Instructor, GA Sydney