Questions to answer before any code is written

Before jumping right into your new modeling task, consider performing a feasibility study. A feasibility study of a predictive model will answer key questions that can help you and the business decide if the modeling task is likely to succeed.

Photo by krakenimages on Unsplash

Feasibility Studies for Machine Learning

A feasibility study is an assessment of the practicality of a proposed project or system.

- Wikipedia

Feasibility studies are common across industries and disciplines. They are an important project planning tool that can help you identify points of failure in a project before any money or time gets invested.

I would argue that feasibility studies are particularly useful for…

It’s not a gift basket or a coffee mug. It’s recognition.

Everyone loves a good specialty jam or quirky desk decoration, but what your co-workers really want this holiday season is recognition.

Photo by Kira auf der Heide on Unsplash

Above and Beyond

Last week I had a frustrating battle with some undocumented code and a wonky database table. I needed to add a record to the table but didn’t have the right tools to do it. The table had text fields that stored gnarly, nested Python dicts, and I kept getting the format wrong. Worse yet, I tried using pandas’ awful to_sql method to write to the table and I ended up mangling all the records (just a local copy, phew).

Many natural language processing tasks can be solved with keyword-based approaches. For those that can’t, you’ll need more advanced NLP approaches. In this article, learn several ways to go beyond keywords, and discover which are best suited for various tasks.

Keywords Are Simple and Powerful

Keyword-based approaches are excellent baselines for various NLP tasks. Let’s explore some examples.

The absolute simplest way to solve tasks such as document classification (either multiclass or multilabel) is what I call “phrase mapping.” For each class, you simply define a set of keywords which, if present, will cause your model to assign the class. A straightforward extension that can reduce false positives is to add a set of negative keywords.

Depending on your task, you might get pretty good recall from this approach. And if you’re lucky and careful, you might get good precision too from the negative keywords…

Office Hours

How quick wins buy time for breakthroughs

Time is running out on your data science project, and you haven’t made a breakthrough yet. Predictive modeling is fraught with uncertainty, but the business doesn’t understand that, or worse yet, doesn’t care. You need to deliver something, and fast. What options do you have?

Photo by Kevin Ku on Unsplash

They Don’t Call It Data Science for Nothing

Data science work is experimental. Many projects that look feasible during planning will ultimately fail. Maybe the input data is less predictive than anticipated. Or the target variable is inconsistent and poorly defined. Or you can’t get access to the data you hoped. …

Photo by Adeolu Eletu on Unsplash

So Much to Learn

It’s been about 5 years since I started my data science career. I’m still learning new skills, techniques, and technologies almost every day. In fact, data science is such a diverse and complex field that I suspect I will never stop learning.

And I’m not alone. Actually, I’ll go out on a limb and say that every data scientist has skill gaps, no matter how senior. New technologies are constantly emerging, and the cutting edge is advancing rapidly.

Strategic Learning

So how can we as data scientists be strategic and intentional with our professional development time? It may be fun to go…

Jared Rand

Data scientist, MBA, entrepreneur, founder at

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store