This technique helped me grow my company’s revenue from $900K to $2M in 2022 (during a “recession”)

Yet 90% of companies don’t know how to use it.

Here’s everything you need to know about text analysis. 🧵

#rstats #stats #datascience #nlp Image
Text is a treasure trove of information.

Seriously… a gold mine. $$$

But it’s not as easy to work with as other types of data like numerical.

Most data scientists just convert text to categorical…

Or even worse, simply don’t use text.
Why is text not being used?

Text requires special techniques like:

1. Tokenization
2. N-grams
3. Stop word removal
4. Stripping characters
5. Counting characters

And formatting text can be tough work.

But a lot of data scientists make 1 big mistake…
What is the Number 1 mistake that most data scientists make when trying to use text?

They go for unstructured text.

PDFs, freeform text fields, customer feedback…

And they miss a goldmine that’s right there waiting for them.
It’s called semi-structured text.

These are text fields that are already in a SQL database.

Things like product descriptions. Or email titles.

And we can use this information to improve model performance.
Now you're probably thinking, great idea! But how?

How 'bout I show you…

I'd like to help you learn Text Analysis for free.

I put together a FREE workshop where I'll uncover how I do text analysis.

Here's what you learn:
1. How to work with text data

Learn how to tokenize structured and unstructured text so you can make it useful for solving business problems
2. My simple technique for automating text data mining

It's 1/10th of the code versus how the way I'm seeing others do it
3. The stupid easy way to improve your model performance with text data

Get the insider's secret to model performance increase + make your company more profitable
4. Get ideas for your future job portfolio

Expand your data science tool chest with Text Analysis

And increase your value to your company.
What's Your Next Step?

My Text Analysis Workshop is completely free.

All you need to do is register & show up.

Register Here: bit.ly/text-analysis-2 Image

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Matt Dancho (Business Science)

Matt Dancho (Business Science) Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @mdancho84

Nov 3
I think the message in Data Science needs to be: Don't believe everything you read. 🧵

#stats #datascience Image
I'd like to thank Nico Cota for pointing me to this modified graphic from a recent Harvard Business Review article on "Prioritizing Which Data Skills Your Company Needs".
You hear Harvard Business Review, & you think this must be legit.

Well, in this case, they dropped the ball.

If you're coming up with an educational plan for your org in 2023, here are some tips:
Read 9 tweets
Nov 2
I’m super excited for today: I’m revealing a secret about text analysis that 90% of data scientists are not using.

It's being overlooked by 90% of data scientists.

And, true story, it helped me double my business in 2022... 🧵

#stats #datascience #rstats Image
Text analysis is a gold mine for customer analytics.

Yet few organizations are harnessing its power.

In fact, I wasn't...

Until I put my money where my mouth is.
True story - Text analysis was part of a solution that helped me increase me double my business in 2022.

Yes, that’s right.

In the middle of a recession, my company doubled its revenue, AND text analysis was a key part.
Read 13 tweets
Oct 11
Network analysis is an amazing tool for business analysis.

But there are a few challenges to be prepared for.

#datascience #rstats #businessanalysis
Network analysis has the potential to identify the most influential customers for a business...

But there are a few challenges that the Data Scientist needs to be prepared for.
One that I often struggle with is determining the right threshold for showing network connections.

Too low and it becomes difficult to find the most important clusters.

Too high and there aren't enough connections to tell anything.
Read 7 tweets
Oct 9
90% of data scientists are overlooking this skill for business analysis.

Yet, it's a gold mine.

Here's why...

#datascience #rstats #business #excel
Whether you realize it or not, your business runs off of customers.

And how they work is based on principles of social psychology.
If you understand which are the most influential customers, then you know how to market to them...

...And knowing their triggers is like adding fuel to a fire. 🔥
Read 8 tweets
Oct 8
Modeling in R is extremely powerful for business analytics...

But many beginners get stuck.

Here's my simple 3-step process to make a linear regression model in R. 🧵

#datascience #business #R #rstats Image
To give some background, these simple 5 lines of code create a basic business solution...

... I'm modeling my ...

Target = bicycle product prices (regression task)
As a function of my predictors:

Predictors = product categories (mountain or road bikes) and bicycle frame material (aluminum or carbon fiber).
Read 10 tweets
Sep 30
The more I dive into Bayesian, the more... my mind is blown.

Here's why. 🧵

#rstats #python #datascience Image
First, Bayesian is like normal regression. Except way better!

It literally solves issues in-sample by sampling. Lots of times!
Second, confidence intervals are realistic.

Unlike normal regression, Bayesian regression accounts for changing variance.
Read 5 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(