Machine Learning basics every manager should know
The use of Machine Learning for business is growing every day. Consequently, there’s an increasing amount of available information about it, which makes it easy to get lost in the Machine Learning jungle.
In this article I’ll provide an overview of the most important Machine Learning concepts, explain how they could be applied to businesses and how to measure the success of it.
What is Machine Learning?
Machine learning is the idea that there are generic algorithms that can tell you something interesting about a set of data without you having to write any custom code specific to the problem. Instead of writing code, you feed data to the generic algorithm and it builds its own logic based on the data.
Why using Machine Learning for business?
Very often we get people contacting us for projects in which they envision the usage of some Machine Learning (ML) techniques to solve a specific problem they have. Sometimes these people do not have any automated system and are solving whatever problem they currently have with human labor. In these cases, the mere fact of being able to produce anything that works reasonably well can make a huge difference for them.
It would be a huge time saver.
But there are other times in which people already have working solutions in place. If the problem is very complex, they might not be happy with how their solution performs. Sometimes even a performant solution might need a replacement.
The complexity of the system will not cease to increase. This is another case in which a ML solution might come in handy: let’s make an algorithm figure out the rules for us. Let’s hope it performs better than any non-ML solution we have come up with so far.
How is Machine Learning applied to business?
Some practical applications of Machine Learning in business are Image Processing, Text Analysis or Data Mining.
Image processing
This is the analysis of images/videos to extract data or do some transformations. Examples are face recognition, self-driving cars and optical character recognition.
Text analysis
In text analysis, information from text is extracted or classified. Examples are spam filtering (as Gmail does), sentiment analysis (identify the mood of the text, ie. positive, negative or neutral) and information extraction (identify key data from a text, for example: an entity).
Data mining
The aim of data mining is to discover patterns or making predictions from data. Examples are anomaly detection (automatic credit card fraud detection), clustering (ie. grouping data based on some characteristics) and predicting variables (ie. predicting stock market prices based on past fluctuations and current events).
What are types of Machine Learning problems?
We can distinct between two main types of Machine Learning problems: Supervised learning and Unsupervised learning. There’s also Semi-supervised learning, which is less used and not discussed further in this article.
Supervised learning
Supervised learning is the most popular type of Machine Learning algorithms. It is used to find patterns in raw data, based on the results of pretrained data.
To get the pretrained data, the data scientist feeds the algorithm with input data and lets the algorithm predict the outcome. For example, it feeds it with a set of dog and cat images and the algorithm needs to assign the corresponding animal to each of them. If it does not predict right, the data scientist acts like a teacher and corrects the results.
This training process goes on until the desired level of performance is achieved.
Unsupervised learning
Unsupervised learning refers to the task of extracting patterns and hidden structure from raw data without extra information, as opposed to supervised learning where labels are needed.
Unlike supervised learning, we don’t have a “teacher” that tells what the correct labels are. In fact, we don’t even know what the set of possible labels is. Algorithms are left to their own devices to find relevant structures in the data. There is no “wrong” or “right” answer here.
What are examples of Machine Learning algorithms?
Classification
A classification task means identifying or predicting which out of a set of categories/labels should be assigned to some data. The output variable is discrete, such as “black” or “white” and “positive” or “negative”. An example of such as task is the spam filter, which assigns a spam or no spam status to every email.
Regression
In contrast to classification problems, the output variable in regression tasks is a real value, such as “dollars” or “weight”, making the prediction a continuous, non-discrete output. A common example of regression is predicting stock market prices.