# Layer-based Composite Reputation Bootstrapping

arXiv: https://arxiv.org/abs/2102.09951 · HTML: https://mlsanity.com/paper/2102.09951/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 56 references that are in the map.
- First posted on arXiv 1 Feb 2021.

## Builds on (most cited first, 6 of 6)

- [Correlation and variable importance in random forests](https://mlsanity.com/paper/1310.5726/) (2013)
- [Towards Explanation of DNN-based Prediction with Guided Feature Inversion](https://mlsanity.com/paper/1804.00506/) (2018)
- [Boosting Random Forests to Reduce Bias; One-Step Boosted Forest and its Variance Estimate](https://mlsanity.com/paper/1803.08000/) (2018)
- [Nonparametric Feature Impact and Importance](https://mlsanity.com/paper/2006.04750/) (2020)
- [Multi-Perspective Trust Management Framework for Crowdsourced IoT Services](https://mlsanity.com/paper/2101.04244/) (2021)
- [Just-in-Time Memoryless Trust for Crowdsourced IoT Services](https://mlsanity.com/paper/2005.14413/) (2020)

## Abstract (arXiv)

We propose a novel generic reputation bootstrapping framework for composite services. Multiple reputation-related indicators are considered in a layer-based framework to implicitly reflect the reputation of the component services. The importance of an indicator on the future performance of a component service is learned using a modified Random Forest algorithm. We propose a topology-aware Forest Deep Neural Network (fDNN) to find the correlations between the reputation of a composite service and reputation indicators of component services. The trained fDNN model predicts the reputation of a new composite service with the confidence value. Experimental results with real-world dataset prove the efficiency of the proposed approach.