This article is a guest post by Agamemnon Papazoglou co-founder of MyJobNow and their story.
MyJobNow offers a web and mobile app that matches job seekers and employers within 48 hours. Essentially it’s a 2-way marketplace where job seekers and companies looking for ideal candidates meet. They make the process simple enough with no endless interviews, paperwork, and long calls. Agamemnon is one of MyJobNow’s founders, and his goal is to build a tech-enabled business that leverages new technologies to offer better or (and) cheaper products for established market needs.
We are excited that Agamemnon shared his customer story. Let’s dig in.
A few introductory words
MyJobNow is a marketplace, and our product/service quality vastly depends on our users. Building complicated and technologically challenging features only work if your users need them. Moreover, understanding what users need is not a trivial task.
Therefore we have invested a significant amount in making MyJobNow operationally efficient to receive, understand and productize user feedback rapidly. We have accomplished that by doing our tech enablement right.
Sales Lead prioritization – A great example
A bit of context
I want to share our latest accomplishment in terms of leveraging technologies, as an excellent example of how we have used state of the art practices and technologies in our stack to optimize sales calls prioritization for new customer conversions. I am going to go through the technologies/tools and how we have used them to solve a specific problem.
Our leads are business owners or HR personnel that wish to hire people. We provide a trial period for our product where leads can post 1 job opening in our platform, receive applications from candidates and communicate with 1 candidate (they have to pay for more).
Our average purchase size at the moment is ~€40 which makes it very challenging to deploy a field sales team. Therefore we have sales reps that call leads (while on their trial period) to convert them.
In the beginning, a blitzkrieg approach was pertinent because our lead generation processes produced just enough leads so that a couple of people were able to handle them. In the past couple of months, we started getting into a phase where inbound leads are way too many (and not an insignificant portion of them irrelevant) for our sales team to handle them all.
So we started prioritizing by using rule-based systems like calling leads that are further down the pipeline in priority to others.
The sales team started taking initiatives which seem to work very well by assessing each lead’s usage and profile before making the call. That yielded great results right away increasing our conversion rates +30% on the attempted conversions. However, things slowed down in terms of call capacity since we had to evaluate every single lead before attempting to call manually.
So the goal became to have some automatic prioritization to reduce the probability of assessing a bad lead as low as possible.
Our Analytics Stack
Here is where we start talking about our tools and how we have used them to create our sales process. So one by one:
- Pipedrive CRM: Pipedrive is a great and extremely customizable CRM. We have done a lot with it, and it would take ages to list all of our customizations. The most important thing to know however is that we have used their API to create a sales funnel using our production data. A deal/person/organization is automatically created when a new user is on-boarded and his/her stage in the pipeline depends on his/her actions in the product.
- Intercom: for messaging & ticketing. Intercom is a great tool, and we have invested a lot into using their SDK in our apps to catch all the events users go through, which gives us massive space for optimized and customized messaging.
- Blendo: My favorite tool of all, blendo makes ETL extremely easy. Blendo replicates consistently all of our CRM, Intercom, Adwords, Facebook ads and many more data into a database that we use for analytics and automation.
- Advertisement platforms: We use Google Ads (AdWords) and Facebook Ads for lead generation.
- Python Pandas & sklearn: Python and sklearn allow us to build simple (and complicated) data-driven analysis and machine learning models in a couple of lines of code.
The goal of this task was to find a way to prioritize leads by the probability of conversion. We tried to see if we can predict whether a lead is likely to convert according to:
- The Customer profile (Location, Industry, etc.) — Pipedrive & production DB data
- The effort invested by Lead (quality of job posting) — Production DB & Intercom Data
- The value received during his/her Trial — Production DB Data
- Timing data — Pipedrive Data
The model used for such a classification is not as crucial as obtaining the feature-set to train the model. A schematic below outlines how our stack is being used to gather the feature-set and productize the model trained.
How Blendo Connects everything
Sales reps can view and input data via the CRM, and Blendo does a great job in gathering everything in one location. With Blendo we sync Pipedrive CRM, Intercom, Facebook Ads and AdWords in our database.
Using the database, populated by Blendo, we were able in less than a couple of days to play around with the data and find a pretty decent model to use.
We could manage all our customer and lead data in one simple, easy-to-use tool. It’s very, very easy to use and powerful.
We can also trust the data now, it is more reliable, and we have more control. When something is broken
or incorrect, I only have to check one or two places. We now use the insights to take action immediately,
and not second guess our tools.
Lead prioritization Model
A Random Forest classifier was the best choice for ~7,000 won/lost deals used as the training set. I was quite surprised by how well this worked. It produced an accuracy of ~76% and f1 score of ~68%.
Recall on predicting conversions was quite low but by adjusting the threshold, I was able to improve this significantly. What was very impressive is the relationship in terms of predicted probability against conversion rates as shown in the figure below.
As a result, we used the predicted probability as a scoring function to prioritize leads.
To productize this model we created a service that rank-orders all open deals every hour according to the trained model’s predicted probability and classifying them:
- A: the top 20% of the population (in terms of scores)
- B: 20–50% of the population
- C: bottom 50% of the population
Given that our conversion rate is ~25% it seemed logical to use these percentages.
What we end up with is with a simple A, B, C classification for all open deals. Sales reps are to prioritize accordingly.
Did it work?
F***k yes! Although a bit preliminary here are the conversion rates on closed deals for the past 15 days:
Lead Class/Conversion Rate
Moreover, our conversions have increased by ~15% in the last couple of weeks 🙂
I am pretty proud of the work we have done at MyJobNow so far. Sales, marketing and customer service teams are happy. They have a better picture, and they focus on the leads that matter to them. We have better insights and help us optimize where to spend our time and energy.
Get more insights to your business
To scale your Analytics Infrastructure into a critical stack accessible by the entire organization, speak with our team today.