Novelty in Recommendation Systems

In this lesson, we will explore the concept of novelty in recommendation systems, a key aspect that complements your understanding of metrics like coverage, discussed in the previous lesson. Novelty measures how unexpected or unique the recommended items are to users. A high novelty score indicates that your recommendation system is providing items that users are less likely to have encountered before, potentially leading to increased engagement and user satisfaction. Balancing novelty with relevance is crucial, as overly novel recommendations may not align with user interests.

Let's briefly discuss the setup we will use as an example for this lesson. Here's a simple setup that prepares us to focus on novelty:

# Basic setup reminder for context
item_popularity = {1: 80, 2: 50, 3: 30, 4: 20, 5: 5, 6: 5, 7: 5}
predicted_items = [1, 5, 3]
total_users = 100  # Example total number of users

This setup includes a dictionary item_popularity representing how often each item appears among users, a list of predicted_items that our system has recommended, and a total_users count.

Novelty quantifies the freshness or unexpectedness of recommendations. We calculate it using the popularity data of the items. Here's how it works conceptually:

• Item Popularity: The frequency with which an item is recommended or interacted with by users. It is important that we can treat this popularity as probability of recommending an item to a user.
• Logarithmic Probability: We use logarithms to assign higher novelty scores to items with lower probability/popularity.
• Normalization: Dividing the sum by the number of predicted items gives us an average novelty score.

We'll now break down the code used to calculate the novelty score step-by-step.

import math

def novelty(predicted_items, item_popularity, total_users):
    sum_log_probabilities = sum(
        -math.log(item_popularity.get(item, 0) / total_users)
        for item in predicted_items if item in item_popularity
    )
    return sum_log_probabilities / len(predicted_items)

# Example data
item_popularity = {1: 80, 2: 50, 3: 30, 4: 20, 5: 5, 6: 5, 7: 5}
predicted_items = [1, 5, 3]
total_users = 100  # Example total number of users

novelty_score = novelty(predicted_items, item_popularity, total_users)
print(f"Novelty: {novelty_score:.2f}")  # 1.47

1. Import Libraries: We start by importing the math library for logarithmic calculations.
2. Function Definition: The novelty function takes predicted_items, item_popularity, and total_users as inputs.
3. Logarithmic Probability Calculation: Using a generator expression, we calculate the logarithm of the inverse probability of each predicted item. The get method with a default value of 0 ensures we handle items not in item_popularity.
4. Summation and Averaging: We sum the negative logarithms for all items in predicted_items and divide by the length of predicted_items to compute the average, returning this value as the novelty score.

The obtained score indicates a moderate level of novelty across the predicted items.