Guest Blogs

Using AI-ML in transactional email marketing

email marketing

Specific problems which are tackled:

  1. Stop spammers from signing up and sending emails
  2. Dynamic warmup based on performance, type of email and reputation
  3. Dynamic email delivery by understanding minute signals from ISPs and your domain/IP reputation and adjust delivery accordingly

Stop spammers from sending emails:

According to statista, around 40% of all sent emails sent worldwide are spam. This was the first problem to solve and we used AI and Bayesian classification to tackle it.

The algorithm looks at 30+ attributes of each domain (like website traffic, DNSBL checks, domain recency, etc) to arrive at a probabilistic score. Higher the probability, the closer the domain would be implicated as email spam.

This is working at a 97% accuracy for us as of today and we’re working to improve to 99+%.

Dynamic Warm-up:

Every domain sending emails for the first time should go through a email warm-up program. The premise of warm-up plan is to send emails gradually and build the reputation over a period of 3-6 weeks.

During the warm-up phase, the number of emails you should send today is a function of emails sent until yesterday plus the level of engagement those emails have generated. Depending on the success of your email program, you move up the warm up slab.

“We wanted to create dynamic warm-up plan that takes in the various factors that impact warm-up and can automatically control the volumes of emails going out.”

As this is a regression-type problem, we used a machine learning technique called Decision Trees to solve this.

For example: if I’ve sent 2,000 emails yesterday and generated an open rate of at least 15% and have less than the threshold of hard bounces & complaints, then increase the volume by 25% the next day.

Currently, this is in beta stage and is enabled for a small set of clients. We will gradually roll out to all our new subscribers in the near future.

Dynamic Email Delivery:

When you send out transactional emails like signup confirmations, you primarily look for speedy delivery whereas for your marketing mails, you would need optimized delivery and better inboxing.

As you can see, different types of emails need different handling and we’re solving this challenge with Neural Networks.

The Neural Net understands minute shifts when it comes to delivery and auto adjusts throughput based on those minute signals.

For example: If the domain hits a certain percentage of invalid users within a minute, the neural network picks up the signal, slows down delivery in the next minute and closely looks at the quality of mailing.

Moving Forward:

Our expansion into machine learning and artificial intelligence in email has just started and the journey so far has been exciting. We’ve lined up some more cool things to do while perfecting our current algorithms.

How does it benefit the email senders?

One word: PEACE !!

Creating a good community of email senders wherein we can decrease the constantly increasing number of spammers in today’s inbox is a philosophy I personally believe in and work with Ppipost in a constant effort to reduce it.

Check Out the New Martech Cube Podcast. For more such updates, follow us on Google News Martech News


Chaitanya Chinta | at Pepipost

Chaitanya Chinta
Cofounder, Deliverability Guy at Pepipost
Chaitanya believes in constant evolution , adaptation and learn to grow. He Is ‘Geek’ by nature and a lover of Linux!!Chaitu (As is fondly called by people around him) is a big time email technology enthusiast and on the constant lookout for up and coming brands and technologies. He is a deliverability expert at Pepipost and a firm believer of creating a Good Email Sending community to fight the nuisance that is SPAM.

Previous ArticleNext Article

Leave a Reply

Your email address will not be published. Required fields are marked *