INBOX INSIGHTS: AI Efficiencies Ripple Effects, ChatGPT Code Interpreter - Trust Insights Marketing Analytics Consulting

INBOX INSIGHTS: AI Efficiences Ripple Effects, ChatGPT Code Interpreter (07/12):: View in browser

👉 Got a Google Analytics 4 emergency? We can help.

July 2023 One Click Poll

Please click/tap on just one answer – this is our monthly survey to see how we’re doing, so please do take it each month!

How likely are you to recommend Trust Insights as a consulting firm to someone in the next 90 days?

We use this information to measure how effective our marketing is. There’s no form to fill out – tapping your answer is literally all there is to it, and then you get to see Katie’s dog.

AI Efficiencies Ripple Effects

AI is great! AI is terrible! AI will take my job! AI will make my job easier! Love it or hate it, AI (artificial intelligence) isn’t going anywhere. Some of you may have concerns about your job security because of AI.

If you’ve introduced AI into your business processes, you may have started to see the efficiencies and cost savings. But what about the rest of your business?

It’s the butterfly effect. One flap of a butterfly’s wing could set in motion a greater series of events, like a typhoon.

Introducing AI might not cause something catastrophic like a typhoon, but there will be a ripple effect on different parts of your company.

Let’s say you started using ChatGPT to write content. You decide that the content is good enough so you stop renewing your write’s contracts. In the short term you’ve saved some money and made the process more efficient.

Now, let’s look longer term. You’ve made one part of your process more efficient using AI, so where is the ripple effect. You have to look backwards and forwards in your process. Start at the beginning of your content creation process. How do you select topics? Who creates your editorial calendar? How does the keyword research get done? Then think about what happens after AI creates the content. Who edits the content? How does it get disseminated? Who keeps the content updated? What metrics do you need to track?

You could argue that AI could handle some of this, or that creating more content wouldn’t have a ripple effect on the other parts of the creation process. What if the stakeholders decide to increase the volume of content because AI can do it so quickly? Now you’re looking at doubling or tripling the workload for the other people involved in the process.

We can start to look at the process beyond content creation and see what the effect is there too. If you’re generating 2x, 5x, or even 10x the amount of content you were before, chances are you’re getting more views, more visits to your website, more engagement. What’s the ripple effect there? Possibly more load to your website, more inquiries from potential customers, more time spent qualifying leads, more sales.

That all sounds fantastic! Sure, but you still need people handling those tasks. Are they equipped to take on more? Let’s say your AI efficiencies generate more sales, more contract, more clients. Now you have to staff up. You need Account Managers, Analysts, Marketers. You need a more robust project management system. All these things come at a cost and a learning curve.

The point is not to scare you aware from using AI in your process to make it more efficient. The point is that you need to look at the bigger picture when optimizing one small part of your process. When Henry Ford started incorporating the conveyer belt into his car manufacturing line it changed everything. He needed to produce more materials to build cars. He needed to hire more people to manufacture the vehicles. He needed to bring on more staff to manage the equipment and sell the cars. One change to the process have have far spreading effect on your overall business.

My advice is to audit your immediate process that you want to optimize and then start to take a look at what else that process touches. Where are the weaker spots in your business that you have to pay attention to if things ramp up? For us, it’s bandwidth. We will need to hire very quickly when our AI processes start generating even more business. It’s a good problem to have, but one that I want to have a plan for.

Are you using AI to make your processes more efficient? Reply to this email and tell me about your journey or come join the conversation in our Free Slack Group, Analytics for Marketers.

– Katie Robbert, CEO

Do you have a colleague or friend who needs this newsletter? Send them this link to help them get their own copy:

https://www.trustinsights.ai/newsletter

In this episode of In-Ear Insights, the Trust Insights podcast, Katie and Chris dive into the buzz around Threads, the new social media platform gaining momentum. Learn how it differs from Twitter, the secrets behind its rapid growth, and why data privacy matters.

Watch/listen to this episode of In-Ear Insights here »

Last time on So What? The Marketing Analytics and Insights Livestream, we discussed podcast marketing measurement. Catch the episode replay here!

This Thursday at 1 PM Eastern on our weekly livestream, So What?, we’ll be talking through the data and analytics behind the Save Warrior Nun campaign with special guest stars. Are you following our YouTube channel? If not, click/tap here to follow us!

Here’s some of our content from recent days that you might have missed. If you read something and enjoy it, please share it with a friend or colleague!

Take your skills to the next level with our premium courses.

📊 Google Analytics 4 for Marketers
🔎 Google Search Console for Marketers

Get skilled up with an assortment of our free, on-demand classes.

In this week’s Data Diaries, let’s take a brain-melting look at the newest AI data analysis tool, GPT-4 Code Interpreter from OpenAI. Housed within the familiar ChatGPT interface, Code Interpreter is part of the $20/month paid plan, and after you see it in action, you’ll wonder why it isn’t $2,000/month. First, we need some data to analyze. Since we opened Trust Insights Academy, we’ve followed a pretty well-known industry strategy: offer up free courses and upsell into paid courses.

The question we want to know the answer to is: does this strategy actually work? We see plenty of course registrations, and we’ve been successful at selling courses, but does this particular marketing strategy work? Let’s have Code Interpreter answer the question.

Before we begin, Code Interpreter is a stupid name for the service. What they should actually call it is Automated Junior Data Scientist, because that’s exactly what it does.

Our first step is to export our orders from the Academy and load them into ChatGPT, along with some basic prompting. Here’s what we said:

Today we’re going to be doing an analysis on the included file. The file is a list of orders for courses, by customer. The Customer ID is the email address, noted in the email field. The courses are in the product field. Some courses are free. Other courses cost money. The way to determine whether something is free or not is in the payment method field, which denotes “no charge” for a free course or a payment method if the course is not free.

The analysis we want to understand is twofold. First, we give away access to free courses to hopefully encourage upsells into our paid courses. We want to know if this strategy is effective. What analysis method would best answer this question?

It responded:

Given your question, one potential analysis approach would be to perform a Cohort Analysis. This type of analysis could provide insights into the behavior of different groups of customers who started their journey with free courses. We could then track if they subsequently purchased paid courses.

Here are the steps we might follow:

Data Cleaning: First, we’ll import the data and clean it as necessary, making sure that the fields are in the correct formats, handling missing values, and so on.

Cohort Identification: We’ll identify different cohorts of customers based on the date when they first enrolled in a free course. These cohorts will represent users who started their journey with a free course in a specific month.

Cohort Metrics: For each cohort, we’ll calculate metrics like:

The number of customers who started with a free course The number of customers who later purchased a paid course The conversion rate from free to paid courses (number of customers who purchased a paid course / total number of customers who started with a free course) Cohort Analysis: We’ll analyze the metrics across different cohorts to understand the effectiveness of the upsell strategy. For instance, we might look at whether conversion rates are improving over time.

However, before we proceed with this approach, let’s first import the data and perform an exploratory data analysis to understand the structure of the data and validate if the proposed method is suitable.

That’s a terrific start. Then it began working – and it does so by writing code:

It does all the work of loading the file, then cleaning and processing the data:

Then it writes the executable Python code to do the cohort analysis:

And finally, it presents us with the analysis:

Oh.

Well… so much for that strategy. What we see is that hundreds and hundreds of people have signed up for our free courses, but of them, exactly 4 have become paying customers. That’s… not a great track record at all. And this is over more than a year’s time, which is plenty of time to accumulate evidence. While this strategy may work for others, it clearly does not work for Trust Insights. Katie and I will have to have a conversation about this strategy’s lack of results.

While this in itself is a useful insight, the big picture takeaway here is what Code Interpreter was able to do. I intentionally did not use the RACE prompt structure we recommend, to better simulate what a non-technical person might ask of the system. It did all the heavy lifting – choosing the analytical method, cleaning and processing the data, and presenting the analysis.

And from start to finish, it took 6 minutes.

I am a skilled data engineer and data scientist. It would take me longer than 6 minutes to perform this analysis, and I would have followed very similar steps (albeit in R, not Python). This tool did a fantastic job for the most part, only needing a couple corrections along the way.

So, am I out of a job? Well… no. The couple corrections I made were subtle math errors. See the final column in the table, Started_Paid? I had to ask it for that specifically because it didn’t create it, and the first iteration of the table, the numbers didn’t add up. So I inspected the code and found that it had made a logical error, which it corrected when I told it to do so. That’s why skilled workers are still needed, because when the machines make errors, the errors aren’t always obvious.

But do I need to hire a junior data scientist now? Not with Code Interpreter. I can have it do a lot of the heavy lifting – the first draft – and then edit, tune, and improve on what it did. Tools like Code Interpreter will be powerful allies to skilled employees, dramatically shortening the time needed to produce powerful analyses. Now that it’s open to the public, you should start testing it yourself, asking it the marketing analytics questions you’ve always wanted answers to, but didn’t have the coding or technical skills yourself to answer.

Here’s a roundup of who’s hiring, based on positions shared in the Analytics for Marketers Slack group and other communities.

Are you a member of our free Slack group, Analytics for Marketers? Join 3000+ like-minded marketers who care about data and measuring their success. Membership is free – join today. Members also receive sneak peeks of upcoming data, credible third-party studies we find and like, and much more. Join today!

Tick-tock, tick-tock! Time’s winding down to secure your spot at MAICON, The Marketing AI Conference, this July 27-28 in Cleveland, Ohio. Not convinced? Picture this: an enlightening pow-wow with the smartest in marketing and AI, including a can’t-miss deep dive into generative AI and large language models by Trust Insights Chief Data Scientist, Christopher Penn. It’s your backstage pass to all things AI and marketing. Need more? Here’s a nifty $150 off the ticket price with the code TRUST150. So, ask yourself, “When did I last turbo-charge my marketing with AI insights?” If that’s a head-scratcher, it’s MAICON o’clock for you! Secure your ticket to the future here: https://trustinsights.news/maicon23. Remember, the early bird catches the AI insights!

Interested in sponsoring INBOX INSIGHTS? Contact us for sponsorship options to reach over 22,000 analytically-minded marketers and business professionals every week.

Where can you find Trust Insights face-to-face?

MAICON, Cleveland, July 2023
Content Jam, September 2023
ISBM, Chicago, September 2023
Content Marketing World, DC, September 2023
Marketing Analytics Data Science, DC, September 2023
MarketingProfs B2B Forum, Boston, October 2023

Going to a conference we should know about? Reach out!

Want some private training at your company? Ask us!

First and most obvious – if you want to talk to us about something specific, especially something we can help with, hit up our contact form.

Where do you spend your time online? Chances are, we’re there too, and would enjoy sharing with you. Here’s where we are – see you there?

Our Featured Partners are companies we work with and promote because we love their stuff. If you’ve ever wondered how we do what we do behind the scenes, chances are we use the tools and skills of one of our partners to do it.

Read our disclosures statement for more details, but we’re also compensated by our partners if you buy something through us.

Some events and partners have purchased sponsorships in this newsletter and as a result, Trust Insights receives financial compensation for promoting them. Read our full disclosures statement on our website .

Thanks for subscribing and supporting us. Let us know if you want to see something different or have any feedback for us!

Leave a Reply Cancel reply

Subscribe to our Weekly Newsletter

Pin It on Pinterest