Qualifying leads is an important activity that sales teams focus to improve their productivity and win customers. We will show you how easy is to build a lead scoring app using machine learning algorithms. For this blog we will use h2o.ai but in the next few days we will show how easy is to build the same using Apache Spark, Azure ML. etc.
Following are the ingredients you need to cook a delicious predictive lead scoring model.
- Lead dataset. For this example we will use the SFDC lead object.
- Build the model. We will be using Machine Learning platform. h20.ai
- Train and validate models.
- Review results
- Visualization – Our favorite Salesforce Wave!
- Prepare the dataset.
This is the first step and in many cases time consuming activity in data analytics. We have to prep the data based on the models we are planning to build. We generated sample lead dataset using mockaroo with the following fields
- Full Name
- Lead source
- Company Size
- isCustomer – This is the objective field that we will be predicting.
|Jose Wood||Yoziofirstname.lastname@example.org||KS||Kansas City||Account Coordinator||Dreamforce||TRUE||Under 1M|
|Paul Kelley||Zoonoodleemail@example.com||SC||Columbia||Environmental Specialist||Onsite||FALSE||Under 1M|
|Louis Stewart||Podcatfirstname.lastname@example.org||NY||New York City||Account Executive||Webinar||TRUE||Between 1M and 5M|
|Johnny Carr||Trudooemail@example.com||FL||Pensacola||Assistant Media Planner||Event||TRUE||Under 1M|
|Theresa Reed||Flipstormfirstname.lastname@example.org||MD||Silver Spring||Computer Systems Analyst IV||Dreamforce||FALSE||Under 1M|
|Louis Evans||Gabvineemail@example.com||MT||Bozeman||Assistant Manager||Demo||FALSE||Between 1M and 5M|
|Judy Anderson||Skajofirstname.lastname@example.org||MO||Jefferson City||Biostatistician IV||Demo||TRUE||Under 1M|
|Mark Vasquez||Buzzsteremail@example.com||NY||Rochester||Geologist IV||Onsite||FALSE||Under 1M|
|Judith Freeman||Linklinksfirstname.lastname@example.org||CA||Stockton||Biostatistician IV||Dreamforce||TRUE||Between 5M and 10M|
2. Build the model
Here are the step by step instructions to build a model in h2o.ai.
- Download the latest edition of h20.ai and run the instance. Its straightforward and should be up and running in few mins.
- Import the files.
Parse the file.
Key thing to note here is choose the right attributes for the fields.
Create test and validation datasets.
Select train (75% split) dataset to build the model.
Choose the algorithm, for this example I chose GBM. Select the train and validation datasets and the objective field we want to predict.
Model completes and results are available to review!
Now use the predict function to run on a test dataset to score leads!
Possibilities are end less
- Fetch SFDC lead dataset, combine with data providers like Axciom, D&B etc
- Associate any other marketing data
- Use h2o.ai to train and validate models.
- Load the results of the datasets in visualization tools like Salesforce Wave for business users to access the results of the predicted status.