🐙 Promptpack: Using ChatGPT to crack your marketing funnel
My colleague Nathan Warren recently shared how he uses ChatGPT's Advanced Data Analaysis to crack the marketing funnel. This was originally published in Exponential View. Enjoy the excerpt!
🎨 Thanks to our sponsor, Masterworks, an investing platform that enables everyday people to invest in multimillion-dollar paintings by artists like Banksy and Basquiat.
Hi,
Nathan Warren here. I recently introduced you to Code Interpreter (now called Advanced Data Analysis) — a powerful feature that allows ChatGPT to write, run and iterate Python code within the browser.
In today’s Promptpack, I will showcase high-level examples of how it can be applied to some marketing activities.
This post is especially dedicated to all business owners and marketers among our readers — I hope it is helpful!
Before we get going, I recommend perusing the initial introduction to the Code Interpreter. This will provide a foundational understanding as we navigate forward.
Data-driven journeys
Today I’ll take you through a proof of concept of how to use ChatGPT’s Advanced Data Analysis for all four parts of the marketing funnel: awareness, consideration, conversion and loyalty.
In these examples, the prompts help pull out a high-level narrative from the data, from which you and your marketing team can dive deeper. The Advanced Data Analysis feature won’t find complex patterns on its own, but it can be a powerful ally in helping you detect and understand them.
We’ll provide initial prompts to kick off the conversation, but ChatGPT’s power is its ability as an interlocutor. A good conversation should spark new thoughts and ideas within you, so please keep the conversation going after the first prompt!
Before we start, some quick tips:
Stage 1: Awareness 👀
This is the first tier of the marketing funnel, the moment when potential customers first encounter your brand or product.
Advanced Data Analysis: To accurately assess the impact of our awareness strategies, we are going to look at our website visits data with Code Interpreter. To get started, upload your dataset containing website visits and channel spend data.
[PROMPT]
Recommended by LinkedIn
Given the attached website visits and spend dataset for our digital marketing channels:
1. Analyse the volume of website visits from different sources over the given period. Identify any consistent trends or notable spikes/dips. Provide a visualisation.
3. Provide a detailed spend analysis for the different channels. Identify which channels are receiving the most investment and assess the cost-effectiveness of this spend.
4. Calculate and visualise the ROI for different channels, determining which channels offer the most value for our marketing investments.
5. Based on the insights, recommend any strategic changes or areas of focus to optimise our digital marketing efforts.
[OUTPUT FROM CHATGPT]
Website Visits Sources: The top graph illustrates the volume of visits from various sources.
[Nathan's comment: The output contained multiple graphs but for the sake of using this space efficiently, I have included only one above].
Insights from the Data:
Visits Volume: Referral visits has been consistently high throughout the quarter, suggesting that partners or external sites are directing a significant number of visitors to the website. Search engine visits also shows an increasing trend, indicating effective SEO strategies.
Spend Analysis: The spend for search engine visits is high, but their ROI suggests that it is a cost-effective channel. In contrast, even though the spend on email campaigns is low, its ROI is also low, indicating it might not be providing value proportional to the investment.
ROI: The ROI for referral visits is particularly high, suggesting that collaborations or partnerships are proving to be a cost-effective strategy. Google Ads also provide a good ROI despite the higher spend.
Recommendations:
Optimise Email Campaigns: Given the low ROI on email campaigns, it's crucial to re-evaluate the strategy. It might be beneficial to segment the audience better, tweak the content, or adjust the sending frequency.
Enhance Referral Partnerships: With the high ROI from referral visits, it might be worth investing more in partnerships or collaborations to further drive visits.
Stage 2: Consideration 🧠
As potential customers become familiar with your brand, they transition to the consideration stage. In this phase, they delve deeper, looking into the specifics of your products or services to see how well they fit with their requirements. This stage requires a keen understanding of an audience’s needs.
Advanced Data Analysis: With the assistance of ChatGPT, we can perform a cluster analysis to segment the audience, revealing their inclinations. We can then tailor content and offers for each individual segment. For this we are using a dataset showing which channels individual customers engage in.
Extra homework: Correlate the segments with website traffic data to identify deeper insights.
[PROMPT]
Given the attached engagement metrics and audience data:
- Perform a cluster analysis to segment our audience.
- Identify the characteristics of each segment.
- Understand which content types resonate most with each segment.
- Provide actionable insights based on this segmentation.
- Recommend strategies to enhance our content approach and further engage each audience segment.
[OUTPUT FROM CHATGPT]
We performed a cluster analysis and segmented the audience into three distinct groups. Here's a breakdown of the engagement characteristics for each cluster:
Cluster 0:
- High engagement with blogs and videos.
- Moderate engagement with webinars and ebooks.
- Lower engagement with infographics.
Cluster 1:
- Moderate engagement across all content types, but particularly higher with infographics.
Cluster 2:
- High engagement with webinars and ebooks.
- Moderate to low engagement with other content types.
Insights & Recommendations:
- Cluster 0: This segment loves both written and visual content. A strategy that combines blogs with embedded videos could be very effective for this group. Given their moderate interest in webinars and ebooks, occasional long-form content or interactive sessions could also be beneficial.
- Cluster 1: This segment shows a more uniform engagement pattern but leans towards infographics. Visual summaries or infographics accompanying detailed content could be a hit with this audience.
- Cluster 2: Webinars and ebooks resonate most with this group, suggesting a preference for in-depth content. Tailored webinar sessions or detailed guides and ebooks could be the way to deepen engagement with them.
In the rest of the post, Nathan delves into other parts of the funnel: conversion and loyalty. Read it in full here, and let us know in comments if you give these prompts a go!
🎨 Today’s edition is supported by Masterworks
Historic growth of 36% with lower risk? It’s possible in this market
It’s a market most people have never considered investing in, but its average prices have risen at an annualized rate of 36% over the last 21 years. Additionally, this market's Sharpe ratio, which measures growth adjusted for volatility, came in at 1.5 – beating the S&P’s .49 over the same time period.
So what is it? Paintings by the world renowned artist Yoshitomo Nara – a market now accessible to anyone, thanks to Masterworks. This unique investment platform enables everyday people to invest in blue-chip art for a fraction of the cost.
Exponential View readers can skip the waitlist with this exclusive link.
-
Disclosure: Past performance is not indicative of future returns, investing involves risk. See disclosures masterworks.com/cd
Co-Founder @ GovernGPT | GenAI for GP's Investor Relations | Y Combinator
1yGood stuff, Nathan!
Business Automation Consultant | Go High Level Automations | Make Automations | Social Media Automations | Lead Generation Expert | No-Code AI Automation Coach | AI & Automations Training
1yIt was really Cool 😍
Realtor Associate @ Next Trend Realty LLC | HAR REALTOR, IRS Tax Preparer
1yThanks for Sharing.