Skip to main content
All CollectionsGetting Started
Building Your Own ML Model with Pecan: A Walkthrough for Everyone
Building Your Own ML Model with Pecan: A Walkthrough for Everyone

Unlock the power of machine learning in 4 easy steps with Pecan—no PhD required! Perfect for BI analysts and data enthusiasts alike.

Ori Sagi avatar
Written by Ori Sagi
Updated over a year ago

Ever thought building a machine-learning model would be out of reach? Well, think again. Pecan has streamlined the entire process, making it as easy as 1-2-3 (and a 4). Whether you're a BI analyst or just starting in predictive analytics, here’s your easy guide to go from zero to predictive hero!

Step 1: Connect Your Data

Before getting started, ensure you have at least 1,000 rows of data—this is your golden ticket to the ML universe. Connecting your data to Pecan is the first stage, and it's as simple as uploading a CSV file or choosing one of our many integrations. No data preparation is needed!

Check out our deep-dive section on data connection for more information.

Step 2: Generate Your Predictive Question

Pecan's predictive chat will not only understand your data needs but also guide you through crafting the perfect predictive question.
Through an intuitive, interview-like conversation, our AI will grasp your unique requirements and then, like magic, generate a custom SQL nutbook tailored just for you. This isn't just a tool; it's a game-changer in data analysis, empowering you to harness the full potential of your data with ease and precision.

Step 3: Fine-Tune Your Predictive Question

Next up is the Nutbook stage, where you can further customize your model. It's like tailoring a suit; you want it to fit perfectly.

In the nutbook, you'll go over the SQL that we generated for you, along with our detailed explanations on what the code is meant to do and why is it important. You can preview the results and adjust the code with simple spark SQL.

This is also the time for you to enrich your model with more attribute tables.
SQL aficionados, this is your playground! Get into the nitty-gritty of the Editor stage here.

Step 4: Train and Evaluate Your Model

Once your nutbook is all set, it's time to train your model. Pecan does the heavy lifting for you here. After the training is complete, you'll get a dashboard that shows how your model is performing. It's like your model's report card but without the dread of parent-teacher meetings. Learn how to interpret your dashboard metrics here.

And voila, you've just built your own machine-learning model! It's that simple.

Ready to take the plunge? With Pecan, you don't need a PhD in Data Science—just a willingness to dive in and let us guide you through the nuts and bolts of predictive analytics.

So, what are you waiting for? Start your 2-week free trial today and join the future of data analytics!

Did this answer your question?