What is machine learning?
It is the use of both historical and current data to make predictions, organize content, and learn patterns about data without being explicitly programmed to do so.
This is typically done using statistical techniques that look for significant events like co-occurrences and anomalies in the data and then factoring in their likelihood into a model that is queried at a later time to provide a prediction for some new piece of data.
Common machine learning tasks include classification (applying labels to items), clustering (grouping items automatically), and topic detection. It is also commonly used in natural language processing. Machine learning is increasingly being used in a wide variety of use cases, including content recommendation, fraud detection, image analysis and ecommerce. It is useful across many industries and most popular programming languages have at least one open source library implementing common ML techniques.
Very basically, a machine learning algorithm is given a “teaching set” of data, then asked to use that data to answer a question.
For example, you might provide a computer a teaching set of photographs, some of which say, “this is a cat” and some of which say, “this is not a cat.” Then you could show the computer a series of new photos and it would begin to identify which photos were of cats.
Machine learning then continues to add to its teaching set. Every photo that it identifies — correctly or incorrectly — gets added to the teaching set, and the program effectively gets “smarter” and better at completing its task over time.
It is, in effect, learning.
Some example of today machine learning.
Malware is a huge — and growing — problem. In 2014, Kaspersky Lab said it had detected 325,000 new malware files every day. But, institutional intelligence company Deep Instinct says that each piece of new malware tends to have almost the same code as previous versions — only between 2 and 10% of the files change from iteration to iteration. Their learning model has no problem with the 2–10% variations, and can predict which files are malware with great accuracy. In other situations, machine learning algorithms can look for patterns in how data in the cloud is accessed, and report anomalies that could predict security breaches.
If you’ve flown on an airplane or attended a big public event lately, you almost certainly had to wait in long security screening lines. But machine learning is proving that it can be an asset to help eliminate false alarms and spot things human screeners might miss in security screenings at airports, stadiums, concerts, and other venues. That can speed up the process significantly and ensure safer events.
Many people are eager to be able to predict what the stock markets will do on any given day — for obvious reasons. But machine learning algorithms are getting closer all the time. Many prestigious trading firms use proprietary systems to predict and execute trades at high speeds and high volume. Many of these rely on probabilities, but even a trade with a relatively low probability, at a high enough volume or speed, can turn huge profits for the firms. And humans can’t possibly compete with machines when it comes to consuming vast quantities of data or the speed with which they can execute a trade. Source: Shutterstock
Machine learning algorithms can process more information and spot more patterns than their human counterparts. One study used computer assisted diagnosis (CAD) when to review the early mammography scans of women who later developed breast cancer, and the computer spotted 52% of the cancers as much as a year before the women were officially diagnosed. Additionally, machine learning can be used to understand risk factors for disease in large populations. The company Medecision developed an algorithm that was able to identify eight variables to predict avoidable hospitalizations in diabetes patients.
The more you can understand about your customers, the better you can serve them, and the more you will sell. That’s the foundation behind marketing personalisation. Perhaps you’ve had the experience in which you visit an online store and look at a product but don’t buy it — and then see digital ads across the web for that exact product for days afterward. That kind of marketing personalization is just the tip of the iceberg. Companies can personalize which emails a customer receives, which direct mailings or coupons, which offers they see, which products show up as “recommended” and so on, all designed to lead the consumer more reliably towards a sale.
Machine learning is getting better and better at spotting potential cases of fraud across many different fields. PayPal, for example, is using machine learning to fight money laundering. The company has tools that compare millions of transactions and can precisely distinguish between legitimate and fraudulent transactions between buyers and sellers.
You’re probably familiar with this use if you use services like Amazon or Netflix. Intelligent machine learning algorithms analyze your activity and compare it to the millions of other users to determine what you might like to buy or binge watch next. These recommendations are getting smarter all the time, recognizing, for example, that you might purchase certain things as gifts (and not want the item yourself) or that there might be different family members who have different TV preferences.
Perhaps the most famous use of machine learning, Google and its competitors are constantly improving what the search engine understands. Every time you execute a search on Google, the program watches how you respond to the results. If you click the top result and stay on that web page, we can assume you got the information you were looking for and the search was a success. If, on the other hand, you click to the second page of results, or type in a new search string without clicking any of the results, we can surmise that the search engine didn’t serve up the results you wanted — and the program can learn from that mistake to deliver a better result in the future.
Natural Language Processing
(NLP) NLP is being used in all sorts of exciting applications across disciplines. Machine learning algorithms with natural language can stand in for customer service agents and more quickly route customers to the information they need. It’s being used to translate obscure legalese in contracts into plain language and help attorneys sort through large volumes of information to prepare for a case.
IBM recently surveyed top auto executives, and 74% expected that we would see smart cars on the road by 2025. A smart car would not only integrate into the Internet of Things, but also learn about its owner and its environment. It might adjust the internal settings — temperature, audio, seat position, etc. — automatically based on the driver, report and even fix problems itself, drive itself, and offer real time advice about traffic and road conditions.