{"id":31090,"date":"2024-03-20T07:20:57","date_gmt":"2024-03-20T11:20:57","guid":{"rendered":"https:\/\/centricconsulting.com\/?p=31090"},"modified":"2024-03-20T07:30:52","modified_gmt":"2024-03-20T11:30:52","slug":"machine-learning-101-part-2-starting-your-first-machine-learning-project","status":"publish","type":"post","link":"https:\/\/centricconsulting.com\/blog\/machine-learning-101-part-2-starting-your-first-machine-learning-project\/","title":{"rendered":"Machine Learning 101: How to Get Started on Your First ML Project"},"content":{"rendered":"
Read part one.<\/a><\/em><\/p>\n Because machine learning (ML) and AI are hot right now, you can easily find a lot of information about it online. Done well, ML \u2014 a kind of AI \u2014 can automate tasks, increasing speed and accuracy while freeing employees to do more valuable, rewarding work.<\/strong> However, ML is both an art and a science, and the best way to learn it is by taking on a small, low-risk project. Don\u2019t damage your reputation by learning just enough about ML online, only to cause problems for your client or employer down the road.<\/p>\n To get started, have your destination in mind and map out how you will get there. We call these steps the ML workflow<\/a>, and they require understanding some key terms and basic concepts. Here is a short glossary:<\/strong><\/p>\n We can see how all of this works together in a simple image:<\/p>\n <\/a><\/p>\n In a webinar<\/a>, our data and analytics experts share six challenges that can derail the productivity of your ML initiatives and why applying MLOps<\/a> can help solve them.<\/p>\n As impressive as ML may seem, don\u2019t forget you need human thought<\/a> to make it all work. Programmers start the process by asking three questions about the problem they want to solve:<\/p>\n Not every problem lends itself to ML. The best automation problems<\/a> are those that involve repeatable, rules-based activities. Problems that you don\u2019t need to repeat, require quick completion, or rely on human intuition are generally not good candidates for ML.<\/p>\n As Gartner points out<\/a>, this question is critical because if data inputs don\u2019t match the defined dataset<\/a>, the model will fail. Think about comparing delivery route data if you measure distances in one dataset in miles and the other in kilometers.<\/p>\n Make sure you have access to enough data to train your model.<\/strong> One of the most common reasons ML projects fail is the lack of data. Data quantity better predicts ML success than data quality.<\/p>\n The diagram below illustrates the ML workflow. As you can see, it is a straightforward process that starts with three phases: sourcing and preparing data, coding the model, training, evaluating, and tuning the model. The last phase begins an iterative process as the algorithm continuously adjusts to the new features it generates.<\/p>\n <\/a><\/p>\n To succeed, you need a large set of training data that includes the feature you want to predict based on the other features. For example, suppose you build your model to predict the sale price of a house. Preparing the data includes:<\/p>\n Develop your model using established ML techniques or by defining new operations and approaches.<\/strong> One of the most common programs used for ML is called Python<\/a>. While a deep dive into Python is beyond our scope in this blog, your first step is to learn basic mathematical concepts like linear algebra.<\/p>\n One good course is Andrew Ng\u2019s Machine Learning on Coursera<\/a>. In addition to linear algebra basics, it will introduce you to the best machine learning techniques and give you hands-on practice applying them to real-world problems. You\u2019ll then be ready to explore the various Python packages, including NumPy<\/a>, Matplotlib<\/a>, Pandas<\/a>, and Scikit Learn<\/a>.<\/p>\n But again, while you can learn basic elements of ML and Python online, online training is no substitute for learning through experience, starting with a small, low-risk project.<\/p>\n Now, you are finally ready to train the model with your training data and evaluate how well it performs.<\/strong> Remember, the larger your data set, the better: More data will help the model work more efficiently, allowing you to validate it for further testing and tuning.<\/p>\n ML has tremendous potential for improving countless areas of our lives. However, to succeed, you must start by understanding what you want your ML project to accomplish and how you will get it across the finish line. Making sure that ML is the best solution for your problem and that you have the amount of data you need before you start is the best pathway to ML success, no matter what program or technology you use.<\/p>\n \n \n
Machine Learning Planning: Thinking It All Through<\/h2>\n
Do I have a well-defined problem to solve?<\/h3>\n
Is ML the best solution for the problem?<\/h3>\n
Do I have a way to measure my Model\u2019s success?<\/h3>\n
The Machine Learning Workflow<\/h2>\n
Source and Prepare Your Data<\/h3>\n
\n
Code Your Model<\/h3>\n
Train, Evaluate, and Tune Your Model<\/h3>\n
Conclusion<\/h2>\n