Regression

Model Scenario

A regression model in machine learning is a type of predictive model used to estimate the relationship between a dependent variable (target feature) and one or more independent variables. It aims to predict continuous outcomes by fitting a line or curve to the data points, minimizing the difference between observed and predicted values. To get the best possible results, we will go through the basics of the Model Scenario. In Model Scenario, you select parameters related to the dataset and model.

Target feature

To run the model, you have to choose a Target Feature first. The target refers to the variable or outcome that the model aims to predict or estimate. In this case, it should be a numerical column.

Model features

You will be taken to the next step where you can choose all the Model Features you want to analyze. You can select which features the model will analyze. Graphite Note will automatically exclude some features that are not suitable for the model and will provide reasons for each exclusion.

Advanced parameters

The Advanced Parameters step in model creation allows users to fine-tune their model settings, enabling behavior similar to how a data scientist would approach the task. These parameters are designed for advanced customization, but for most users, it is recommended to leave the default settings as they are to ensure optimal performance.

Users can explore and adjust these parameters to tailor the model to specific needs. For detailed explanations of the different advanced parameter settings, refer to the Advanced Parameters section.

Actionable Insights Goal

The Generate Actionable Insights section allows users to enable the automatic generation of actionable insights based on model predictions, enhanced with the capabilities of generative AI. The insights are generated in the language specified in the User profile information page under the AI Generated Content Language settings.

You can activate this feature by checking the Generate Actionable Insights box. Once enabled, the system will use model predictions to create insights tailored to your needs.

Specify the primary objective of the analytics by completing the Goal field. This includes choosing an action (e.g., “Increase” or “Decrease”) and the specific metric or outcome (e.g., average of “Monthly Charges” ). These inputs guide the insights generation process.

Additional Context is an optional field to provide extra details about your business, target audience, or specific focus areas. Examples might include demographics (e.g., focusing on age group 25-35) or market focus (e.g., targeting the European market). This helps align the generated insights with your business narrative.

Model training

Moving forward, you'll see a comprehensive list of preprocessing steps that Graphite Note will apply to prepare your data for training. This enhances data quality, ensuring your model produces accurate results. Typically, these steps are performed by data scientists, but with our no-code machine learning platform, Graphite Note handles it for you. After reviewing the preprocessing steps, you can finish and Run Scenario.

The training duration may vary depending on the data volume, typically ranging from 1 to 10 minutes. The training will utilize 80% of the data to train various machine learning models and the remaining 20% to test these models and calculate relevant scores. Once completed, you will receive information about the best model based on the F1 value and details about training time.

Model Performance

To interpret the results after running your model, go to the Performance tab. Here, you can see the overall model performance post-training. Model evaluation metrics such as F1 Score, Accuracy, AUC, Precision, and Recall are displayed to assess the performance of classification models. Details on Model metrics can also be found on Accuracy Overview tab.

On the performance tab, you can explore six different views that provide insights related to model training and results: Overview, Key Drivers, Impact Analysis, Model Fit, Training Results and Details.

Overview

Opening the Performance tab on a regression model takes you to Overview, where top-line fit metrics—R², MAPE, MAE, RMSE, and MSE—summarise accuracy and error at a glance. Just below, auto-generated text describes your dataset structure, target-column distribution, and the run parameters used, giving instant context for how those metrics were achieved. For deeper diagnostics, see the full Model Overview documentation.

Key Drivers

Key Drivers indicate the importance of each column (feature) for the Model's predictions. The higher the reliance of the model on a feature, the more critical it is. Graphite uses permutation feature importance to determine these values.

Impact Analysis

The Impact Analysis tab allows you to select various features and analyze, using a bar chart, how changes in each feature affect the target feature. You can switch between Count and Percentage views.

Model Fit

The Model Fit Tab displays the performance of the trained model. It includes a stacked bar chart with percentages showing comparison between known outcomes (historical) and model predicted outcomes.

Training Results

The Training Results tab lists every regression algorithm Graphite Note tried during the automated training run. In the example above, 75 % of the data (5 282 rows) was used for training and 25 % (1 761 rows) for testing.

For each candidate model you’ll see the key fit metrics side-by-side—R-Squared, MAPE, MAE, RMSE, and MSE—so you can compare accuracy and error at a glance. The model that delivers the best result for the primary metric (R-Squared by default) is shaded green and marked with a check icon.

When you click a row, Graphite reveals the Model Hyper Parameters panel beneath the table, showing the exact settings (e.g., learning-rate, max_depth, regularisation values) that produced the winning run. This makes it easy to audit, reproduce, or fine-tune your model outside the no-code environment if needed.

Details

The Details tab shows the results of the predictive model, presented in a table format. Each record includes the predicted label, predicted probability, and predicted correctness, offering insights into the model's predictions, confidence, and accuracy for each data point. Dataset test results can be exported into Excel by clicking on the XLSX button in the right corner.

Take actions with Regression

Once the model is trained, you can use it to predict future values, solve multi-class classification problems, and drive business decisions. Here are ways to take action with your Regression model:

Actionable Insights

If you enabled Generate Actionable Insights while defining your scenario, the trained model produces two distinct insight layers that appear under the Actionable Insights screen:

• Strategic Summary – an executive-level brief that turns the model’s key drivers into clear business goals, KPIs, and evidence-based strategies. Use this narrative when you need to present findings to leadership, define high-level initiatives, or align cross-functional teams.

• Feature Insights – a driver-by-driver deep dive that shows feature importance, value-range multipliers (for example, “tenure 1–6 months increases churn 2.2×”), and plain-language recommendations for each range or category. Refer to this view when you want granular guidance for pricing, segmentation, or campaign design.

Both tabs are generated automatically by Graphite Note’s generative-AI engine as soon as training completes. Open Actionable Insights to review them, then follow the suggestions to move from prediction to measurable business impact. For a detailed walkthrough of each tab, see the dedicated Actionable Insights documentation page.

Predict

After building and analyzing a predictive model using Graphite Note, the Predict function allows you to apply the model to new data. This enables you to forecast outcomes or target variables based on different feature combinations, providing actionable insights for decision-making.

What-If Scenario Predictions: You can manually input values for relevant features (e.g., tenure, PaymentMethod, Contract) to simulate specific scenarios. Once the values are entered, clicking the Predict button provides the predicted outcome as a numerical value.

CSV File or Dataset Predictions: You can upload a CSV file containing data for multiple observations to generate predictions in bulk or you can also utilize existing datasets from Graphite Note for batch predictions, leveraging previously uploaded data.

Create Notebook

You can share your prediction results with your team using the Notebook feature. With Notebooks, users can also run their own predictions on your Regression model.

Notebooks allow you to create various visualizations with detailed descriptions. You can plot model results for better understanding and enable users to make their own predictions. For more information, refer to the Data Storytelling section.