Sales Funnel Optimization

Background

The sales funnel illustrates the process that leads go through before they become customers. Sales funnels have four stages: awareness, interest, desire, and action. The goal of any sales funnel is to move as many leads as possible through it, which requires sales funnel optimization.

The large majority of companies—74%—say converting leads into customers is their top priority. 

A well-optimized sales funnel will have a high conversion rate at each stage, and it will be easy to identify which stages are causing bottlenecks. In this post, we’ll cover how to optimize your sales funnel using Akkio’s no-code machine learning.

Traditional Sales Funnel Optimization

Traditional sales funnel optimization involves a lot of shooting in the dark. OptinMonster recommends trying out strategies like blogging, social networking, PPC, public relations, contact forms, autoresponders, referrals, and more to help convert leads.

That’s a lot to consider, let alone actually execute on. Marketers make careers on each of those strategies individually, with titles such as Content Marketer, Social Media Marketer, PR Strategist, Email Marketer, and so on.

In other words, it’s unrealistic to just try everything under the sun to increase conversions. There needs to be a data-driven strategy, that tells you exactly what to change. This is where AI comes in.

Sales Funnel Optimization With AI

We can use Akkio to make predictions on historical sales data, and deploy a model to focus our sales efforts on the leads most likely to convert.

To get started, sign up to Akkio for free. As with any machine learning task, the first step is getting historical data and picking a column to predict.

Historical Data

In our video tutorial, the historical data is a Kaggle dataset of 9,240 leads for online courses, with descriptive attributes like Lead Source, Total Time Spent on Website, Total Visits, and Last Activity. The dataset includes a target variable called “Converted.”

We can use machine learning to calculate the probability that a lead bought an online course, and then prioritize leads with a high probability of converting.

You can upload any dataset you want by simply clicking “Upload Dataset.” Below, we’ll explore how to connect Salesforce to Akkio, as this is a common source of sales data. First, we simply create a new flow, and connect our Salesforce account.

Note that, to connect Akkio with Salesforce, you need a Salesforce Edition with API access, which can be Enterprise, Unlimited, Developer, or Performance. The Group, Essentials, and Professional Editions do not have API access.

If you don’t already have a relevant Salesforce account, you can sign up for a Salesforce Developer Trial, which includes example datasets, such as “opportunity.csv,” which we’ll use below to predict the probability of a lead being won.

Building the Model

Now, we can click on the second step in the AI flow, which is “Predict.” Under “Predict Fields” you can select the column to predict, named “Won.”

Then just hit “Create Predictive Model,” and you’re done! In the lead scoring demo, the model has already been made, but it takes as little as 10 seconds to train a model from scratch. You can also select a longer training time—from 1 to 5 minutes—for potentially more accurate models. Keep in mind that longer training times aren’t always better, and may lead to overfitting.

Also note that you don’t pay for model training time, unlike with many typical automated machine learning tools, so feel free to build as many models as you’d like.

Analyzing the Model

After a model is created, you get a simple overview, which highlights the top fields, model prediction quality, sample predictions, and more.

There’s also the option to “See Model Report,” which lets us easily collaborate with others and share these model details with anyone, even if they don’t have an Akkio account.

In short, we’ve discovered that it’s very easy to build a highly accurate model to score leads.

Deploying the Model

Now that we’ve built a model, it’s time to deploy it in the real-world.

With Akkio, it becomes trivial to deploy complex machine learning models, whether through Salesforce, Google Sheets, Snowflake, a web app, Zapier, or the Akkio API.

If you’re less technical, you could deploy the model in practically any setting with Zapier, a no-code automation tool that connects tools with “Zaps.” Zapier allows you to link up thousands of different tools, so no matter where your data is coming from, it’s easy to connect it to Akkio to get a prediction.

If you’re looking for more technical power, you can also use Akkio’s API, which is formatted as a Curl command, allowing you to send a GET request that contains your flow key, API key, and input data, and get a prediction back.

Since we’ve made predictions based off of Salesforce data, let’s deploy our model back in Salesforce as well, and update our Salesforce data with our predictions. Simply add a third step, and select Salesforce as the output. From there, configure your output settings according to the desired schedule, run rules, and so on.

And you’re done! Once you’ve filled in the desired configuration, simply hit “Deploy,” and you’ll have a live AI model making predictions on Salesforce data.

Summary

We’ve explored how increasing conversion rates can be a key driver of business success. If you’re only focused on lead generation and not lead conversion, you’re leaving money on the table. Highly successful landing pages and sales teams convert upwards of 10% of their leads, which makes their lead generation efforts much more fruitful.

Using Akkio’s no-code AI, you can effortlessly build and deploy lead scoring models, and operate more effective sales and marketing teams.