The Jalandhar Student Who Built Her First ML Model in 30 Days

It Started With One Google Search

Simran was sitting in her second-year college hostel room in Jalandhar, scrolling through job postings that all wanted the same thing: "machine learning experience." She had none. She wasn't even sure what a model actually was, beyond the word showing up in every tech article she skimmed.

"I typed 'what is machine learning for beginners' into Google at 11 PM," she says. "I didn't expect to still be reading about it at 2 AM."

That's usually how it starts for most students. Not with a grand plan, but with curiosity that refuses to let you sleep.

The First Week Was Confusing, Not Exciting

Here's something people don't tell you: the first few days of learning ML rarely feel exciting. They feel confusing. Simran spent her first week just trying to understand the difference between AI, machine learning, and deep learning — three terms she'd been using interchangeably without knowing they meant different things.

She also hit the question almost every beginner asks: "Do I need to be a math genius for this?" Her answer, looking back, was no — but she did need to stop avoiding the math entirely. A little statistics, a little linear algebra, learned alongside actual coding rather than from a textbook first, made the concepts click.

By day seven, she wasn't building anything yet. She was just starting to see the shape of what she'd need to learn — Python basics, data handling, and the logic behind how a model actually "learns" from data instead of being explicitly programmed.

That shift, from confusion to clarity, is usually the real starting point of any ML journey.

Week Two: Python, Data, and the First "Aha" Moment

By the second week, Simran wasn't just reading — she was writing code. Small scripts at first. Loading a CSV file. Cleaning messy data with pandas. Plotting a graph and actually understanding what it showed.

This is usually where students in Jalandhar either lose momentum or find their footing. The temptation to jump straight into flashy projects is strong, but Simran stuck to fundamentals a little longer than she wanted to. At TechCadd's Machine Learning course in Jalandhar, her mentor encouraged her to focus on understanding the basics before rushing into complex projects.

"I got impatient," she admits. "I wanted to build something 'real' by day ten. My mentor told me to slow down and actually understand what a dataset was telling me before feeding it into a model."

That patience paid off. Around day twelve, she trained her first model — a simple linear regression predicting house prices from a public dataset. It wasn't accurate. It wasn't impressive. But watching numbers on her screen actually predict something, even roughly, was the moment machine learning stopped being an abstract concept and became something she could touch.

Common Mistakes She Made (So You Don't Have To)

Simran is upfront about her mistakes, because she thinks that's more useful than pretending the process was smooth.

She initially skipped understanding why her model was wrong, focusing only on getting a working script. She also fell into the classic beginner trap of copying code from tutorials without typing it herself — which felt productive but taught her almost nothing.

The turning point was when she started asking "why" instead of just "how." Why does this algorithm work for this kind of data? Why did accuracy drop when she changed one variable? At TechCadd, these were the kinds of questions her mentor encouraged her to explore rather than simply memorising code.

That question-first mindset is often what helps students move beyond tutorials and start understanding how machine learning actually works.

By the end of week two, she had rough code, a semi-working model, and — more importantly — a real sense of how the whole process fit together.

For Simran, Techcadd's Machine Learning course in Jalandhar wasn't about learning everything in a few days. It was about building the right foundation, practising consistently, making mistakes, and gradually learning how to turn data into something meaningful.