Dave on Data

The Dave on Data mission is to empower any professional (or team) with the DIY data science skills needed to unleash the power of AI technologies like Copilot in Excel.

What gets left out of the AI Hype Cycle is this:

AI will make you (or your team) wildly more productive.

**BUT**

You must have the requisite skills to make the most of AI.

**AND**

If these skills are lacking, you will not be able to recognize (and correct) the AI when it makes mistakes.

BTW - AI makes mistakes all the time.

Take Microsoft's Copilot in Excel AI as an example.

The "magical" scenarios where Copilot analyzes data using a few clicks and a couple of short prompts rely heavily on two things:

Python
Machine learning

Here's the thing, however. 

I've tested Copilot in Excel, which rarely generates the correct Python/machine learning code.

As the DIY data scientist, this is where you unleash Copilot's power.

I can teach you these DIY data science skills.

Regardless of role. Regardless of background.

Founder

TDWI

I develop and deliver live training experiences on data science topics such as data analysis and predictive analytics (e.g., machine learning). I focus on accelerating the data science journey for teams and organizations using a practical hands-on approach.

Training can be delivered virtually or in person with your team. The following offerings are certified by TDWI and can be taught using R or Python:

👉 Machine Learning Bootcamp
👉 Visual Data Analysis
👉 Linear/Logistic Regresion

💻 Learn more: https://daveondata.com/live-analytics-training

Data Science Consultant & Instructor

Schedulicity

VP of Analytics

Data Science Dojo

VP of Data Science

Microsoft

Sr. Director, BI and Analytics

Principal Program Manager

Sr. Director, Platform Architecture

Principal Architect

Ascentium Corp

Associate Partner, Solution Architect

Safeco Insurance

IT Architect

e-software, Inc.

Software Design Engineer

Programmer Analyst

I help ANY professional or team have more impact using data. Analytics demystified.

Want to differentiate yourself at work with Excel skills? Leaders aren't excited about this in 2025:

- Using PivotTables
- Knowing many Excel functions

You know what they're excited about: AI

And that means Copilot in Excel.

Here are the 4 steps to build the skills you need to master Copilot in Excel and impress your manager, business stakeholders, and executives:

1) Ignore "prompt engineering."
2) Learn Python.
3) Learn DIY data science.
4) Recognize hallucinations.

I want to help you own the future of Microsoft Excel.

I will help you get started today - for free.

Join 1,000s of professionals building skills for the future: 
https://daveondata.com/newsletter

I'm being surprised each week by what is not being taught about forecasting. For example, I'm taking online certification courses in financial planning and analysis (FP&A).

Despite the importance of forecasting to FP&A deliverables, none of the forecasting courses I've taken cover this critical concept:

The best forecasters first establish a baseline.

Simple forecasting models, in many situations, can provide useful forecasts. In some cases, these simple models outperform more complicated forecasting solutions.

But here's the thing.

If you never evaluate a baseline, how would you know?

Here are 3 ways to easily establish a baseline using Microsoft Excel:

- Linear regression
- Moving averages
- Naive forecasts

You don't need to be a math genius to use the above to establish your forecast baseline.

For example, you can use Excel to add a trend line to your data, which will provide the trend line's equation (see the example image below). 

You then use this equation to make forecasts.

David Langer

I help professionals and teams build better forecasts using machine learning with Python and Python in Excel.

I recently took an FP&A certification course on forecasting. There was no coverage assessing the quality of a forecast. 😮

This is amazing to me, given the importance of forecasts in so many finance deliverables (e.g., 3-statement models).

If you're a finance professional, or any professional for that matter, who wants to build better forecasts using Microsoft Excel, check out my tutorial series.

Greetings, DIY data scientist! You may be wondering why I'm doing a tutorial series on forecasting using Microsoft Excel, instead of my "more technica

Open article: Forecasting with Excel Part 3: Measuring Accuracy by David Langer • 6 min read

Forecasting with Excel Part 3: Measuring Accuracy

Tired of data conferences that are just 45-minute marketing presentations? What if I told you there was a data conference where you could learn hands-on skills with:

- Machine learning
- Text analytics
- Forecasting

All with no Python experience required? Check this out.

I'm teaching my top-rated Machine Learning Bootcamp at the TDWI Orlando conference next month:

3 days of in-person classroom instruction
My 4-hour Python Quick Start tutorial
15 hands-on labs to build skills
1-on-1 help if you need it
A TDWI certificate

Learn more and register here: https://lnkd.in/e64_gDUh

Do you want to build better forecasts with Microsoft Excel? Here are 4 steps you can do today to rock your forecasts.


1) Understand seasonality.

The key to the best forecasts is understanding the seasonality of your business process. We're all familiar with yearly seasonality:

- Spring/Summer/Fall/Winter
- New Year's resolutions
- Black Friday in retail

However, seasonality also comes in other forms:

- Fewer calls in the evening
- More sales on weekends

You must know your seasonality for the next step.


2) Collect enough data.

The most common mistake I see is that professionals do not collect enough data for their forecasts.

While there's no "magic number" for the amount of data you need to build better forecasts, here are some rules of thumb:

- Get as much data as you possibly can.
- At a minimum, you want at least 3 cycles of seasonality.

For example, let's say you're forecasting monthly sales and you have yearly seasonality. You would want at least 36 months of data.

Here's why.


3) You must test your forecasting models.

The second most common mistake I see professionals make is not testing their forecasts.

Since forecasting is all about predicting the future, we need a way to simulate the future for testing. This is where splitting your data is critical:

- Building the model on the oldest data.
- Testing the model with the newest data.

At a minimum, you need one full seasonality cycle for testing.

By the way, you also need to do this.


4) Establish a baseline.

Simple forecasting models can work surprisingly well in certain situations.

That's why you should always establish a baseline using a simple model (e.g., a moving average) before using a more complex model.

To continue the example from Step 2, you would use a moving average to create forecasts for the last 12 months of sales data.

You record the accuracy of the simple model on the test data.

You then compare this accuracy to Excel's FORECAST.ETS() function.



📌 P.S. - Do you want to learn more about building better forecasts using Microsoft Excel?

26,829 professionals are receiving weekly tutorials via my free LinkedIn newsletter.

Join us: https://lnkd.in/exdhEPpB

I got some excellent news today. Barnes & Noble has bought copies of my upcoming book for hundreds of their stores! 🎉 🥳 🍾

I always love pivoting from my social media feeds dominated by AI posts to conversations with clients.

The gap between social media and the real world is like the Grand Canyon. 🤣

Why am I teaching 26,719 professionals how to measure the accuracy of their Microsoft Excel forecasts tomorrow morning? The answer might surprise you.

Recently, I've become fascinated with the area of financial planning and analysis (FP&A).

This fascination includes taking online certification courses from a major vendor in the FP&A space, including courses on forecasting.

What I found most surprising about these courses is that, despite the importance of forecasting in FP&A, no best practices are taught.

For example, measuring the accuracy of the forecast before using it in an FP&A deliverable. 😮

This is one reason subscribers to my LinkedIn newsletter are receiving a multi-part tutorial series to build better forecasts using Excel.

Want in?

Subscribe to my free LinkedIn newsletter today: https://lnkd.in/exdhEPpB

Taplio

David Langer's Linkedin Analytics

David Langer

Performance ScoreDavid Langer's LinkedIn Performance

Who is engaging with David

David Langer's Best Posts (last 30 days)

Ready to grow your LinkedIn presence?

Taplio

.css-1jgreyo{background-image:linear-gradient(284deg, rgba(39,43,72,1) 0%, rgba(33,47,183,1) 100%);color:transparent;-webkit-background-clip:text;background-clip:text;}David Langer's Linkedin Analytics

David Langer

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}David Langer's LinkedIn Performance

Who is engaging with David

David Langer's Best Posts .css-1emoo84{font-size:var(--chakra-fontSizes-md);font-weight:400;color:var(--chakra-colors-gray-600);}(last 30 days)

Ready to grow your LinkedIn presence?

David Langer's Linkedin Analytics

Performance ScoreDavid Langer's LinkedIn Performance

David Langer's Best Posts (last 30 days)