AI for email marketing – practical e-commerce
4 mins read

AI for email marketing – practical e-commerce

Optimizing delivery times was my first experience using artificial intelligence in email marketing. The concept is to send an email when a recipient is likely to engage with it based on their historical opens and clicks – a form of machine learning.

Apple’s iOS privacy changes have made open rates less reliable, but it used to be a solid strategy. Many email platforms offered send time optimization, including Mailchimp, Iterable, and IBM Watson Campaign (now Acoustic).

AI continues to disrupt email marketing. Platforms like Grammarly, ChatSonic, ChatGPT, and Jasper can generate high-quality, personalized content fast.

For example, I asked ChatGPT to “write a paragraph of email marketing copy promoting my retail brand’s new 20% discount and include a mention of the socially responsible program we are implementing to help a Donate part of our earnings to the community”.

Here is the answer:

Exciting news! Get ready to save big on all your favorite products from our retail brand. For a limited time, enjoy a 20% discount on all items in store and online. In addition, with every purchase you not only do something good for yourself, but also give something back to the community. We’re proud to announce our new socially responsible program, where a portion of our earnings are donated to local charities. Shop now and feel good knowing you are making a positive contribution while saving on quality products.

Exciting news!  Get ready to save big on all your favorite products from our retail brand.  For a limited time, enjoy a 20% discount on all items in store and online.  In addition, with every purchase you not only do something good for yourself, but also give something back to the community.  We're proud to announce our new socially responsible program, where a portion of our earnings are donated to local charities.  Shop now and feel good knowing you are making a positive contribution while saving on quality products.

ChatGPT responded to a marketing copy request in less than 3 seconds. Click on the image to enlarge it.

Impressive! The response took less than 3 seconds. It needs a bit of rewriting, but it’s a decent base.

ChatSonic’s response to the identical prompt is even better, with additional details such as a discount code and informal wording.

Welcome to [Retail Brand], the place to find the best products to make your life easier. We’re pleased to announce that for a limited time you’re enjoying a 20% discount on our entire range – simply use code DISCOUNT20 at checkout. And to make the deal even sweeter, we’ve launched a new socially responsible program. For every purchase you make, a percentage of the proceeds are donated directly to local charities. So do your part and shop with us today!

Welcome to [Retail Brand], the place to find the best products to make your life easier.  We're pleased to announce that for a limited time you're enjoying a 20% discount on our entire range - simply use code DISCOUNT20 at checkout.  And to make the deal even sweeter, we've launched a new socially responsible program.  For every purchase you make, a percentage of the proceeds are donated directly to local charities.  So do your part and shop with us today!

ChatSonic’s response added details such as a discount code and informal wording. Click on the image to enlarge it.

Advantages and disadvantages

AI is a powerful tool, but it’s not perfect. The best results combine AI output with human input. Here are my pros and cons for using AI for email marketing.

Advantages

  • efficiency. AI can analyze data and create high-quality copies much faster than a human.
  • Personalization. AI can personalize content for each recipient.
  • Optimization. AI can test variations of text and optimize campaigns for better engagement and conversions.
  • scalability. AI can analyze and automate massive volumes of email, help large businesses, and otherwise free up time for other tasks.

Disadvantages

  • lack of creativity. AI-generated content can lack the creative flair of humans.
  • Limited understanding of context. AI does not (yet) have a human understanding of language, tone and context.
  • Mistake. AI-generated copy contains errors and omissions.
  • dependency. Organizations that rely on AI may struggle to adapt when the technology becomes outdated, limited, or unavailable.

future of AI

Neil Patel, the author and influential marketer, believes that Google will “crush” ChatGPT. In a LinkedIn post, Patel wrote, “Once Google starts taking their collected data and developing/training their own AI tools, chatGPT won’t be able to keep up.”

DeepMind, a subsidiary of Google’s parent company Alphabet, is a world-leading artificial intelligence laboratory. (DeepMind’s CEO recently addressed the platform’s ambitions.)

Regardless, in 2023, AI-generated content is only as good as the data it was trained on. AI is a boon for marketers, but human verification is crucial to avoid mistakes and differentiate a brand. It’s the human element that makes email marketing successful.