Insurance pricing on price comparison websites via reinforcement learning

ArXiv ID: 2308.06935 “View on arXiv”

Authors: Unknown

Abstract

The emergence of price comparison websites (PCWs) has presented insurers with unique challenges in formulating effective pricing strategies. Operating on PCWs requires insurers to strike a delicate balance between competitive premiums and profitability, amidst obstacles such as low historical conversion rates, limited visibility of competitors’ actions, and a dynamic market environment. In addition to this, the capital intensive nature of the business means pricing below the risk levels of customers can result in solvency issues for the insurer. To address these challenges, this paper introduces reinforcement learning (RL) framework that learns the optimal pricing policy by integrating model-based and model-free methods. The model-based component is used to train agents in an offline setting, avoiding cold-start issues, while model-free algorithms are then employed in a contextual bandit (CB) manner to dynamically update the pricing policy to maximise the expected revenue. This facilitates quick adaptation to evolving market dynamics and enhances algorithm efficiency and decision interpretability. The paper also highlights the importance of evaluating pricing policies using an offline dataset in a consistent fashion and demonstrates the superiority of the proposed methodology over existing off-the-shelf RL/CB approaches. We validate our methodology using synthetic data, generated to reflect private commercially available data within real-world insurers, and compare against 6 other benchmark approaches. Our hybrid agent outperforms these benchmarks in terms of sample efficiency and cumulative reward with the exception of an agent that has access to perfect market information which would not be available in a real-world set-up.

Keywords: Reinforcement Learning, Dynamic Pricing, Contextual Bandits, Model-Based RL, Revenue Management

Complexity vs Empirical Score

• Math Complexity: 6.0/10
• Empirical Rigor: 6.5/10
• Quadrant: Holy Grail
• Why: The paper presents a novel hybrid RL framework with model-based and model-free components, requiring advanced mathematical formulation, while also demonstrating practical application using synthetic data and benchmarking against multiple approaches.

  flowchart TD
    R["Research Goal: Develop an optimal PCW pricing strategy for insurers"] --> M["Methodology: Hybrid RL Model<br/>(Model-Based offline + Model-Free CB)"]
    M --> D["Input: Synthetic Commercial Insurance Data<br/>(reflecting real-world constraints)"]
    D --> CP["Computational Process:<br/>1. Train agents offline via Model-Based RL<br/>2. Deploy contextual bandit for dynamic updates"]
    CP --> E["Experimental Evaluation<br/>vs 6 Benchmarks"]
    E --> F["Key Findings:<br/>• Hybrid agent superior in sample efficiency & reward<br/>• Avoids cold-start & adapts dynamically<br/>• Outperforms standard RL/CB approaches<br/>(excluding unrealistic perfect-info benchmark)"]