Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

5.2%10.5%15.7%21.0% · May 202619922001200920182026
48 results for peer predictions

OKDDip uses diverse peers to improve online knowledge distillation.

problem Early saturation in group-based distillation.
method Two-level distillation with multiple auxiliary peers and a group leader, using attention-based aggregation weights.
result OKDDip consistently gives better performance than state-of-the-art approaches.

The study improves credit evaluation in peer-to-peer lending using machine learning.

problem Traditional credit histories are insufficient for distinguishing good from bad borrowers.
method Used machine learning classification and clustering algorithms to predict creditworthiness.
result Achieved 65% F1 and 73% AUC on LendingClub data, identifying key secondary attributes.

Two-stage scoring approach for P2P lending improves loan profitability prediction.

problem Class imbalance and lack of profitability prediction in existing scoring methods.
method Integrates credit scoring and profit scoring using wide and deep learning.
result Two-stage scoring approach outperforms existing methods in loan profitability prediction.

This paper uses LSTM to predict P2P lending default rates, improving accuracy with macroeconomic data.

problem Predicting default rates in the P2P lending market for risk assessment.
method Long Short Term Memory (LSTM) model with unemployment rate as a macroeconomic factor.
result LSTM model outperforms traditional time series models in predicting default rates.

Bitcoin price prediction models fail to outperform a simple 'today's price' baseline, especially at longer horizons.

problem Lack of robust models that consistently outperform a naive price predictor at various horizons.
method Surveyed peer-reviewed papers, categorized by evaluation methodology, contrasted with social media discourse, and proposed methodological standards.
result No peer-reviewed study has shown robust superiority over the naive baseline across multiple market regimes at short-to-medium horizons.

Model aggregates answers with peer predictions, inferring world states.

problem Aggregating answers from multiple respondents without assuming consensus correctness.
method Probabilistic model incorporating respondent signals and predictions.
result Model infers world states and respondent expertise, outperforming other models.

BrainTorrent uses peer-to-peer FL for medical image segmentation without a central server.

problem Lack of sufficient annotated data for personalized medical models.
method Peer-to-peer federated learning framework without a central server.
result BrainTorrent outperforms traditional server-based FL and achieves similar performance to pooled data training.

Study finds Aave token network has core-periphery structure, with high decentralization predicting better returns.

problem Understanding the actual decentralization in DeFi token transactions on the Ethereum blockchain.
method Applied social network analysis to measure decentralization in Aave token transactions.
result A more decentralized Aave token network predicts higher returns and lower volatility.

Paper identifies bias and strategic behavior in crowdsourced performance assessments.

problem Crowdsourced performance assessment risks personal interest introducing distortions.
method Developed a method to identify bias and strategic behavior using a rich dataset.
result Discovers a pattern of 'discriminatory generosity' in peer evaluation.

Paper introduces a peer-to-peer ML algorithm for personalized models with privacy.

problem Leveraging data from many agents for personalized models while maintaining privacy.
method Fully decentralized, asynchronous, differentially private algorithm with provable convergence.
result Algorithm outperforms previous work in non-private settings and significantly improves under privacy constraints.

We provide two distributed confidence ball algorithms for solving linear bandit problems in peer to peer networks with limited communication capabilities. For the first, we assume that all the peers are solving the same linear bandit problem, and prove that our algorithm achieves the optimal asymptotic regret rate of a…

2016-04-26abs ↗pdf ↗

Backtests of structured strategies lose much of their predictive power in live trading.

problem Uncertainty in how marketed backtests predict live performance of structured strategies.
method Analysis of 1,726 structured strategies from ten global institutions.
result Raw backtests have limited portability into live trading and deteriorate sharply.

PEER tackles multi-response regression with incomplete outcomes efficiently.

problem Challenges in estimating, predicting, and computing with large-scale multi-response regression and incomplete outcomes.
method PEER converts multi-response regression into parallel univariate-response regressions.
result PEER achieves consistency in estimation, prediction, and variable selection.

Study shows peers' graduation improves residents' success in TCs.

problem Identifying peer influence in therapeutic communities adjusting for latent homophily.
method Used data on affirmations and exit dates to form peer networks, modeled latent homophily, and proposed bias correction methods.
result Positive effect of peers' graduation on residents' graduation, varying by gender, race, and role model definition.

Study predicts P2P lending platform failures using machine learning.

problem Predicting failures of P2P lending platforms in China.
method Used machine learning models with filter and wrapper methods, forward selection, and backward elimination.
result Identified robust variables for predicting platform failures with high AUC and F1 scores.

Study optimal risk sharing in decentralized peer-to-peer markets with robust risk measures.

problem Optimizing risk sharing in decentralized markets with non-convex risk measures.
method Characterization of Pareto-optimal allocations using robust distortion risk measures and probabilistic risk aversion.
result Shape of allocations depends on agents' tail risk assessments.

This paper evaluates methods for predicting credit risk in social lending, especially for imbalanced data.

problem Predicting credit risk in imbalanced social lending environments.
method Empirical comparison of various classifier-resampling techniques, focusing on random forest and random under-sampling.
result Combining random forest and random under-sampling may be an effective strategy for predicting credit risk in social lending.

High-dimensional adjustment reduces bias in estimating peer effects from observational data.

problem Estimating peer effects from observational data is challenging due to confounding variables and high bias.
method Used high-dimensional adjustment with propensity score models to estimate peer effects.
result High-dimensional adjustment produces estimates of peer effects statistically indistinguishable from randomized experiments.

Research uses private information from borrower networks to predict P2P lending profitability.

problem Improving credit scoring in P2P lending networks.
method Applied machine learning algorithms to graph and location metrics of borrower networks.
result Graph topology and borrower location information predict loan profitability, reducing error by 4%.

The paper analyzes reinsurance strategies in peer-to-peer insurance schemes.

problem Strategic interaction between plan managers and reinsurers in P2P insurance.
method Develops two game-theoretic contract designs: Pareto and Bowley designs, deriving optimal contracts and analyzing their welfare effects.
result The Bowley design yields a unique optimal contract, while the Pareto design allows for multiple Pareto-optimal contracts.

In massive open online courses (MOOCs), peer grading serves as a critical tool for scaling the grading of complex, open-ended assignments to courses with tens or hundreds of thousands of students. But despite promising initial trials, it does not always deliver accurate results compared to human experts. In this paper,…

2013-07-09abs ↗pdf ↗

Paper predicts transaction confirmation time in Ethereum blockchain using machine learning.

problem Estimating transaction confirmation time in Ethereum blockchain.
method Uses machine learning, specifically Random Forest Regressor and Multilayer Perceptron, to predict transaction confirmation time.
result Proposed model shows improved accuracy in predicting transaction confirmation time compared to statistical models.

Machine learning analyzed peer reviews to find differences in quality by journal impact factor.

problem Determining if higher journal impact factors correlate with more thorough or helpful peer reviews.
method Hand-coded and machine-learned analysis of 10,000 peer review sentences from 1,644 journals.
result Peer reviews in higher impact factor journals are more thorough in discussing methods but less helpful in suggesting solutions and providing examples.

This paper builds a recommendation system for borrowers on P2PL platforms to lower interest rates.

problem Help borrowers make wise decisions on P2PL platforms to achieve lower interest rates.
method Developed a recommendation system to suggest the type of loan borrowers should apply for.
result Borrowers can achieve lowered interest rates with a higher likelihood of getting funded using the recommendation system.

FedCoin uses blockchain to fairly distribute incentives in federated learning.

problem Fairly incentivizing data owners in federated learning with privacy concerns.
method FedCoin uses a blockchain-based peer-to-peer payment system with a proof of Shapley (PoSap) protocol to calculate and distribute Shapley Values.
result FedCoin accurately computes Shapley Values and promotes high-quality data contributions.

This study compares decentralized banks and finds some lack decentralization.

problem Decentralized banks do not fully decentralize transactions as expected.
method Network analysis of transaction data from four banks using core-periphery features.
result MakerDao and Compound are more decentralized than Aave and Liquity.

Develops a risk score to assist ECMO planning for critically ill patients with viral or unspecified pneumonia.

problem Lack of a risk score to guide ECMO planning for critically ill patients.
method Leverages machine learning to develop the PEER score.
result PEER score predicts mortality and decompensation in patients eligible for ECMO.

New models automate support group formation in online health communities.

problem Challenges in traditional support group formation methods for scalability, static categorization, and insufficient personalization.
method Two novel machine learning models: gDMR and gSTM, integrating user content, demographics, and network data.
result Models outperform baselines in predictive accuracy, semantic coherence, and internal group consistency.

Study higher-order spin glass models for social network behavior with peer-group effects.

problem Modeling correlation phenomena on social networks with peer-group effects.
method Inference in higher-order Ising models to recover coefficients and peer-group effects.
result Strong concavity of log pseudo-likelihood implies statistical error rate of sqrt(d/n) for MPLE.

Decentralized learning of personalized models and collaboration graphs without central coordination.

problem Training personalized models and collaboration graphs in a decentralized manner without a central coordinator.
method Alternates between training models given the graph and updating the graph given the models, using peer-to-peer exchanges.
result Communication-efficient approach that avoids exchanging personal data, with benefits demonstrated on synthetic and real datasets.