Research shows that the average sales cycle has increased by almost 25% in the last 6 years. At the same time, fewer salespeople are hitting their quotas. Long, drawn-out sales cycles are taking up valuable time that could be spent closing more deals.
In the current market, companies need to be more aggressive to stay afloat. Sales teams are consistently being asked to close more deals, which is tough for any team to manage. Luckily, Akkio can help.
The Akkio platform can help sales teams predict the time-to-close for their leads and prioritize which opportunities to pursue. With a simple click of a button, Akkio will generate a prediction for the probability of a lead converting into a closed deal within a certain number of days.
This calculated time-to-close can take into account factors like the number of interactions that have taken place between the lead and the company in question, which can be monitored over time to gauge how well the lead is responding.
Once a time-to-close model has been created, it's possible to see which leads are most likely to close the fastest, and then prioritize them accordingly. The sales team can then work on closing deals with these high-value leads while simultaneously reducing their efforts with lower-value prospects.
Sales teams often struggle to keep up with an ever-growing workload, but Akkio's system makes it easy for them to maximize their efforts by putting high-value leads at the top of their priority list.
We’ll use a dataset of SaaS customers from Kaggle, titled Sales Pipeline Conversion at a SaaS Startup. This dataset includes around 78,000 rows of customer sales data, including information like the client’s city, opportunity size, client revenue, and sales medium.
Crucially, the file includes our desired target variable, called sales velocity, which is another way of describing time-to-close. We can use machine learning to estimate the time-to-close for any new lead or customer, and then prioritize business resources accordingly.
Predicting time-to-close is a challenging problem because it requires us to make a number of assumptions about the relationships between the different variables in our dataset. But we’ll show you how to use machine learning to estimate this time-to-close accurately, and then use that output to generate a prioritized sales pipeline.
First, we’ll just download the dataset as a CSV, and upload it to Akkio in a new model flow. You'll get a preview of the dataset, including modifiable data types, columns, and row count.
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 “sales velocity.”
You can add or remove as many columns as you’d like, and we'll build a model based on the selected columns. Then just hit “Create Predictive Model,” and you’re done.
You can select a longer or shorter training time—ranging from 10 seconds to 5 minutes—for potentially more accurate models. Keep in mind that longer training times will not always necessarily perform better.
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.
After a model is created, you get a simple overview, which highlights the top fields, model prediction quality, sample predictions, and more. We’ll also see customer segments, showing, for instance, customer profiles with the lowest and highest values of sales velocity.
This indicates which segments will need greater sales resources, as well as which segments can be targeted as quick wins. Segment 3, for instance, has the lowest values for sales velocity, with a typical deal closing in just one month. These are smaller clients with lower revenue and fewer employees. We can continue targeting those clients through direct marketing as low-hanging fruit.
On the flip side, the slowest sales velocity customer is someone with high revenue and a lot of employees. These clients typically take over 2 months to close, which means that adequate sales resources would need to be allocated when such a client is in the pipeline. These kinds of leads are typically gained through partnerships, rather than direct marketing efforts.
Armed with these insights, we can now prioritize our sales efforts. 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 predict time-to-close.
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. Deployment via web app is an easy way to instantly serve predictions. It’s also possible to deploy through Salesforce, Google Sheets, Snowflake, and the Akkio API, with many more methods coming soon.
Further, 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, even if you don’t have any technical expertise.
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.
We’ve explored how sales velocity is a useful metric that can be used to assess and improve sales efficiency. We’ve seen how to find the fastest selling companies, and we’ve also looked at the profiles of slower movers. We've then seen how to deploy machine learning to estimate this metric for any new lead or customer, which can be used to generate a prioritized sales pipeline.
We’ve now covered all the key steps to take when predicting time-to-close for your leads and customers. So, are you ready for your first prediction? Get started with Akkio today, and start making smarter decisions with your data.