Skip to content

usdaed

  • Science
  • Who is Denis Avetissian?

Science

Shadowing the Market: A Guide to Index Tracking

08.01.2026 by qfx

Across three modeling paradigms designed for index tracking, cumulative returns of the best-performing portfolios consistently mirror those of the S&P 500 index, demonstrating effective replication of market performance.

This review examines the diverse strategies used to replicate financial indexes, offering a critical comparison of traditional and modern approaches.

Categories Science

Can Machines Spot the Bots? Assessing AI Text Detection

08.01.2026 by qfx

Confusion matrices demonstrate the performance of Logistic Regression, BiLSTM, and DistilBERT models on the test set, revealing their respective classification accuracies and error patterns.

As artificial intelligence writing tools become increasingly sophisticated, accurately identifying AI-generated text is a growing challenge.

Categories Science

Decoding the Story in the Stock Market

08.01.2026 by qfx

The temporal distribution of research papers reveals patterns in scholarly activity over time.

New research details how natural language processing can systematically analyze financial narratives to understand their influence on market dynamics.

Categories Science

Stopping Fake News Before It Goes Viral

08.01.2026 by qfx

AVOID cultivates a simulated ecosystem of agents initialized from distilled real-world commentary personas, enabling the propagation of information within a virtual environment to preemptively identify and counter disinformation campaigns.

A new simulation framework uses AI-powered agents to model how news spreads online, offering a powerful approach to detect misinformation early.

Categories Science

Spot the Fake: AI Pinpoints Image Manipulation with Unprecedented Accuracy

08.01.2026 by qfx

A new deep learning approach combines the power of Vision Mamba and guided graph neural networks to precisely locate alterations in both subtly and heavily manipulated images.

Categories Science

Spotting Shifts and Explaining Why: A New Era for Time Series Analysis

08.01.2026 by qfx

The framework establishes a robust changepoint detection system-enhanced by retrieval-augmented generation-that not only identifies shifts in time series data but also leverages hybrid semantic-temporal search to incorporate private knowledge and, critically, employs large language models to infer plausible causal events underlying these detected changes-effectively moving beyond mere anomaly detection to reasoned explanation.

Researchers have developed a framework that combines statistical methods with the power of large language models to automatically detect and explain changes in data over time.

Categories Science

Unmasking Fake Audio: A New Approach to Deepfake Detection

07.01.2026 by qfx

The architecture proposes an approach to large language models centered around three distinct, fine-tunable modules, acknowledging that any such system is less a constructed entity and more a predicted pattern of eventual compromise - a carefully cultivated vulnerability destined to bloom with time, rather than a fortress against failure.

Researchers have developed a novel framework that uses the power of large language models and reinforcement learning to identify manipulated audio across a wider range of scenarios.

Categories Science

Powering Up Price Prediction: A New Approach to Electricity Forecasting

07.01.2026 by qfx

A reduced linear model within a multilayer perceptron architecture successfully forecasts hourly electricity prices.

A novel hybrid deep learning method is improving the accuracy and efficiency of day-ahead electricity price forecasting across European markets.

Categories Science

Forging Financial Futures: Synthetic Data for a New Era

07.01.2026 by qfx

PersonaLedger establishes a dataset linking defined user personas to detailed sequences of transactional and payment activity, providing a foundation for analyzing behavioral patterns through financial interactions.

Researchers have developed a new framework for creating realistic and privacy-preserving financial transaction data, unlocking opportunities for innovation and analysis.

Categories Science

From Bids to Best Policies: Smarter Auto-Bidding with Generative AI

07.01.2026 by qfx

The study demonstrates that system performance is exquisitely sensitive to hyperparameter selection, suggesting that graceful degradation-rather than outright failure-is achievable through careful calibration of underlying mechanisms, as evidenced by the nuanced response to variations in these critical settings [latex] \Delta \theta [/latex].

A new approach to automated advertising bidding leverages generative models and Q-value regularization to learn optimal strategies from existing data.

Categories Science
Older posts
Newer posts
← Previous Page1 … Page25 Page26 Page27 … Page88 Next →
© 2026 usdaed • Built with GeneratePress