23 Sep Machine Learning – Introduction with an example

Machine Learning is a subset of Artificial Intelligence. The computer is fed with data and information. This gives these systems the ability to learn and enhance from experiences. The process happens without being explicitly programmed.

In layman’s language, consider Machine Learning to be a process of training a piece of software (called a model) to make predictions. This process can also generate content from data.

Consider a model in machine learning as a mathematical relationship derived from data. A Machine Learning system uses this to make predictions.

Machine Learning Example: Predicting stock prices

Let’s see an example to predict stock prices:

The traditional approach to predicting stock prices includes the role of financial analysts. They will use historical stock prices, economic indicators, and financial reports of a company to create complex mathematical models.

These factors of these complex models may include interest rates, company earnings, market trends, etc. The financial analysts would then use these models to predict future stock prices. This approach is complex and time-consuming. Also, only experts with incredible domain knowledge can work on such an approach.

Machine Learning Approach

Let us now see an approach that uses machine learning to ease the work:

1. Collect Data: A large dataset of historical stock prices, trading volumes, economic indicators, news articles, etc. is gathered for our model. This is our relevant data and is quite important for the next steps.
2. Preprocess Data: Clean and preprocess the data. This includes handling missing values, removing duplicates, etc. Here, training and testing datasets will be created
3. Train the Model: One of the crucial steps is to train the model. The clean and preprocessed data from the above step will be used to train a machine learning model, such as a neural network. The model would now learn patterns and relationships in the data. This will be done indicative of future stock price movements.
4. Make Predictions: After the training, our Machine Learning model can now be fed with the input data. Since we are predicting stock prices, therefore the current market data will be taken as input. This is done to get our output i.e. predicting future stock prices.

Note: Our model continuously enhances as more data is fed.

So, summarizing what we did above and displaying them as the following steps for an ML model. These will be discussed in the later chapters:

1. Define the Objective
2. Collect and Prepare the Data
3. Select the Algorithm
4. Train the Model
5. Test the Model
6. Predict
7. Deploy

If you liked the tutorial, spread the word and share the link and our website Studyopedia with others.

For Videos, Join Our YouTube Channel: Join Now

Read More:

• Applications of Machine Learning
• Machine Learning vs Deep Learning
• What is a Machine Learning Model
• Steps to Build a Machine Learning Model
• Train/ Test in a Machine Learning Model
• Inductive vs Deductive Machine Learning
• Bagging vs Boosting in Machine Learning
• What are Large Language Models (LLMs)
• Artificial Intelligence vs Machine Learning vs Data Science vs Deep Learning
• Types of Deep Learning
• Techniques for implementing Generative AI
• What are Transformers in Deep Learning