Search

In the realm of financial analytics, leveraging unstructured data, such as earnings conference calls (ECCs), to forecast stock volatility is a critical challenge that has attracted both academics and investors. While previous studies have used multimodal deep learning-based models to obtain a general view of ECCs for volatility predicting, they often fail to capture detailed, complex information. Our research introduces a novel framework: \textbf{ECC Analyzer}, which utilizes large language models (LLMs) to extract richer, more predictive content from ECCs to aid the model's prediction performance. We use the pre-trained large models to extract textual and audio features from ECCs and implement a hierarchical information extraction strategy to extract more fine-grained information. This strategy first extracts paragraph-level general information by summarizing the text and then extracts fine-grained focus sentences using Retrieval-Augmented Generation (RAG). These features are then fused through multimodal feature fusion to perform volatility prediction. Experimental results demonstrate that our model outperforms traditional analytical benchmarks, confirming the effectiveness of advanced LLM techniques in financial analysis., Comment: 9 pages, 1 figures, 2 tables

The integration of Artificial Intelligence (AI) techniques, particularly large language models (LLMs), in finance has garnered increasing academic attention. Despite progress, existing studies predominantly focus on tasks like financial text summarization, question-answering (Q$\&$A), and stock movement prediction (binary classification), with a notable gap in the application of LLMs for financial risk prediction. Addressing this gap, in this paper, we introduce \textbf{RiskLabs}, a novel framework that leverages LLMs to analyze and predict financial risks. RiskLabs uniquely combines different types of financial data, including textual and vocal information from Earnings Conference Calls (ECCs), market-related time series data, and contextual news data surrounding ECC release dates. Our approach involves a multi-stage process: initially extracting and analyzing ECC data using LLMs, followed by gathering and processing time-series data before the ECC dates to model and understand risk over different timeframes. Using multimodal fusion techniques, RiskLabs amalgamates these varied data features for comprehensive multi-task financial risk prediction. Empirical experiment results demonstrate RiskLab's effectiveness in forecasting both volatility and variance in financial markets. Through comparative experiments, we demonstrate how different data sources contribute to financial risk assessment and discuss the critical role of LLMs in this context. Our findings not only contribute to the AI in finance application but also open new avenues for applying LLMs in financial risk assessment., Comment: 24 pages, 7 figures, 5 tables, 1 algorithm

Here, the synthesis of polyglobalide (PGl) by enzymatic ring-opening polymerization (e-ROP) is investigated, using pressurized carbon dioxide (CO2), pressurized CO2 + dichloromethane (DCM), and pressurized propane as solvents. Particularly, the effects of phase equilibrium on the course of e-ROP and PGl final properties are discussed. The partition coefficients of CO2, DCM, propane, globalide and PGl were calculated with help of thermodynamic models, providing proper understanding of monomer partitioning in the reaction system. Reactions performed in pure CO2 resulted in monomer conversions of 100%. Besides, when only one liquid phase was present inside the reactor, PGl samples presented low polydispersities and high average molecular weights. When carried out in CO2 + DCM, e-ROP resulted in lower monomer conversions and PGl samples with higher polydispersities and lower average molecular weights. Finally, reactions carried out in pressurized propane (200 bar) produced PGl samples with the highest average molecular weights among the analyzed products., Comment: 41 pages, 9 figures, 8 tables

We investigate the emergence of both quantum anomalous Hall and disorder-induced Anderson Chern insulating phases in two dimensional hexagonal lattices, with antiferromagnetically ordered 3Q state and in the absence of spin-orbit coupling. Using tight-binding modeling, we show that such systems display not only a spin-polarized edge-localized current, the chirality of which is energy dependent but also an impurity-induced transition from trivial metallic to topological insulating regimes, through one edge mode plateau. We compute the gaps' phase diagrams, and demonstrate the robustness of the edge channel against deformation and disorder. Our study hints at the 3Q state as a promising building block for dissipationless spintronics based on antiferromagnets., Comment: 7 pages, 8 figures

We propose that topological spin currents flowing in topologically non-trivial magnetic textures, such as magnetic skyrmions and vortices, produce an intrinsic non-adiabatic torque of the form ${\bf T}_t\sim [(\partial_x{\bf m}\times\partial_y{\bf m})\cdot{\bf m}]\partial_y{\bf m}$. We show that this torque, which is absent in one-dimensional domain walls and/or non-topological textures, is responsible for the enhanced non-adiabaticity parameter observed in magnetic vortices compared to one-dimensional textures. The impact of this torque on the motion of magnetic skyrmions is expected to be crucial, especially to determine their robustness against defects and pinning centers., Comment: 7 pages, 4 figures

In this paper, we apply Value-at-Risk (VaR) approaches on the problem of yearly electric generation management. In a classical approach, the future is modelled as a markov chain and the goal is to minimize the average generation cost over this uncertain future. However, such a strategy could lead to big financiallosses if worst case scenarios occur. The two VaR approaches we propose, precisely aim at robustifying the model. On a practical point of view, it amounts to introduce a new set of constraints modelling the uncertainties in the original optimization problem or equivalently to change the dual objective function. The new optimization problems are solved as efficiently as the nominal model. Numerical simulations are presented and discussed for this application.