Likelihood to Buy: Event Weights

Prerequisites

• You have access to the Data Studio

• You had an overview of your Likelihood to Buy model

• You had a look at the Insights page

How to read the Event weights table?

The Event weights tab section lists the different events and aggregated events, and how much each of them weight in the scoring. 

The Event weights table displays the events in the same order as the Lift graph of the Insights page.

• Event: user-friendly name of the event performed by a user, mapped from the behavioral data from your integration (in app.HG Insights.com > mapping > event mapping).

  • Tips: events like "Email - At least X activities in the last X day(s)" are aggregated events. Learn more. 

• Importance (in points): weight of the event 

• Lifespan (in days): the decay of the event in days. For example: if lifespan = 90 days, this means that 90 days after doing this event, this event has no contribution to the lead or account likelihood to buy score. The decay maximum value is 90 days.

Did X value:

• High Statistical Significance (Did X > 100)

  • What it means: Events performed by 100+ people in the training dataset

  • How to use: These weights should be prioritized and are most reliable

• Moderate Statistical Significance (10 < Did X < 100)

  • What it means: Events performed by 10-100 people

  • How to use: Consider these weights as directional indicators

• No Lift Available (Did X = 0)

  • What it means: No one in the training dataset performed these events

  • How to use: Only assign meaningful weights if you have strong business justification

• No Statistical Significance (Did X < 10)

  • What it means: Events performed by fewer than 10 people

  • Recommendation: Default to weight of 1 unless there's strong business justification

Columns related to the Event mapping:

• Activity type: when building the event mapping we categorize events ("meta events") in different segments (Web Activity, Marketing Activity, Product Usage, Sales Activity, Email Activity...) 

• Negative User Activity: when building the event mapping we also define if the event is more of a "negative action" (deleted account, unsubscribe from newsletter, declined invitation ...) than a positive event (showing that the user is engaging with the product / company).

  • We would typically assign negative weights to negative user activities

Columns related to Historical analysis (based on the people in the training dataset and their activity 3 months before), providing information and guidance on how the factor loading and decay are and should be configured:

• Suggested importance = the recommended weight (in points) to attribute to this event, which is calculated based on the lift. 

• Suggested Lifespan = the recommended Lifespan to attribute to this event, which is calculated based on how frequently an event is done. (The more frequent, the lower the lifespan should be)

• Average for converted: how many times was this event performed on average by a person that converted

• Average for non-converted: how many times was this event performed on average by a person that did not convert 

• Did X: how many people performed this event 

  • If Did X >= 100 we estimate that the sample of people is large enough to derive conclusions (statistically significant) 

  • If Did X < 100 we estimate that the sample of people is too small to derive conclusions

• Did not do X: how many people did not perform this event

• Did X conversion rate: conversion rate of people who did this event

• Did not do X conversion rate: conversion rate of people who did not do this event

• Lift: Ratio between the conversion rate of people who did the event to the overall average conversion rate of the training dataset 

  • when lift > 0 it means that someone performing this event is more likely to convert 

  • when lift < 0 it means that someone performing this event is less likely to convert

• Recall conversions: proportion of converters that did this event

• Recall non-conversions: proportion of non-converters that did this event

• Average for converted * factor loading: multiplication of the event weight and the average number of occurrences of this event per conversion. This gives us an idea of how many points would be assigned to someone who usually does this event with that many occurrences.

How are the weights and decays configured?

The automatic suggestions for weights and decays are calculated using three key factors:

1. Lift: How strongly the event correlates with conversion

2. Statistical Significance: Number of people who performed the event (Did X)

3. Frequency: How often converters perform this event (Average for converted)

The calculation prioritizes:

- Events with higher lift values

- Events with stronger statistical significance

- Events that occur consistently among converters

The weight and decays automatically suggested are derived from a calculation based on the lift of the event, how many people have done this event (did X) and how often is the event performed by converted (average for converted). 

However, you can manually change the weights and decays to tweak the model according to your Sales team feedback, your analysis, or business needs. 

For example:

• You'd like to make sure that registering to a webinar does not bump the person automatically to a high likelihood to buy, therefore you would want to decrease the weight of the event "Registered to Webinar" to be under the threshold of the medium/high segment (see in Thresholds tab)

• You'd like to make sure that people who requested a demo are scored low after 30 days if they have only performed this action, therefore you would want to decrease the decay of the event "Requested a demo" to 30 days.

Best Practices for Event Weight Configuration

1. High-Impact Events

  - For events like "Requested Demo" or "Started Trial", consider both weight and lifespan carefully

  - Example: A demo request might deserve high weight (20+ points) but shorter lifespan (30-45 days)

2. Negative Actions

  - Always assign negative weights to negative user activities

  - Example: "Unsubscribe from Newsletter" should have a negative weight

3. Catch-all Events

  - Set weight to 0 for "Other [integration] activity" events

  - These are automatically created events that weren't explicitly mapped in event mapping

4. Frequency Consideration

  - For high-frequency events, use lower lifespan values

  - For rare but significant events, use longer lifespan values