Linear regression as a basic model

Case 5. Predicting market salary

Estimating a market salary is a classic regression task: given a candidate’s features (experience, tech stack, company size, remote work), we want to output a number – the expected salary.

Below is a minimal RubixML baseline: we train Ridge regression on a tiny dataset and then predict salary for a new candidate. This demonstrates the mechanics, not a "real" market model.

$x_1$ – experience (years);
$x_2$ – technologies score (a simplified numeric score for the tech stack);
$x_3$ – company size (level: 1 = small, 2 = medium, 3 = enterprise);
$x_4$ – remote work (1 = yes, 0 = no);

Linear regression model: $\hat{y} = w_0 + w_1 x_1 + w_2 x_2 + w_3 x_3 + w_4 x_4$, where $\hat{y}$ is the salary prediction.

Example of code:


<?php

use Rubix\ML\Datasets\Labeled;
use Rubix\ML\Regressors\Ridge;

// Features: experience_years, technologies_score, company_size_level, remote
$samples = [
    [1, 2, 1, 1],
    [3, 4, 2, 1],
    [5, 6, 3, 0],
    [7, 8, 3, 1],
    [10, 10, 3, 1],
];

// Target: salary_usd
$labels = [
    1500,
    2800,
    4500,
    6200,
    8000,
];

$dataset = Labeled::build($samples, $labels);

$model = new Ridge(1.0);
$model->train($dataset);