Tootfinder

Investment Portfolio Optimization Based on Modern Portfolio Theory and Deep Learning Models
Maciej Wysocki, Pawe{\l} Sakowski
https://arxiv.org/abs/2508.14999 https://

Investment Portfolio Optimization Based on Modern Portfolio Theory and Deep Learning Models
This paper investigates an important problem of an appropriate variance-covariance matrix estimation in the Modern Portfolio Theory. We propose a novel framework for variancecovariance matrix estimation for purposes of the portfolio optimization, which is based on deep learning models. We employ the long short-term memory (LSTM) recurrent neural networks (RNN) along with two probabilistic deep learning models: DeepVAR and GPVAR to the task of one-day ahead multivariate forecasting. We then use …

Establishing Technical Debt Management -- A Five-Step Workshop Approach and an Action Research Study
Marion Wiese, Kamila Serwa, Anastasia Besier, Ariane S. Marion-Jetten, Eva Bittner
https://arxiv.org/abs/2508.15570

Establishing Technical Debt Management -- A Five-Step Workshop Approach and an Action Research Study
Context. Technical debt (TD) items are constructs in a software system providing short-term benefits but hindering future changes. TD management (TDM) is frequently researched but rarely adopted in practice. Goal. This study aimed to establish a TDM process in an IT company based on a predefined workshop concept. We analyzed which research approaches practitioners adopted for each TD activity and the TDM's long-term effect on TD awareness. Method. We used action research (five action cycles in …

Through-the-Cycle PD Estimation Under Incomplete Data -- A Single Risk Factor Approach
Barbara D\"om\"ot\"or, Ferenc Ill\'es
https://arxiv.org/abs/2508.15651 …

Through-the-Cycle PD Estimation Under Incomplete Data -- A Single Risk Factor Approach
Banks are required to use long-term default probabilities (PDs) of their portfolios when calculating credit risk capital under internal ratings-based (IRB) models. However, the calibration models and historical data typically reflect prevailing market conditions. According to Basel recommendations, averaging annual PDs over a full economic cycle should yield the long-term PD. In practice, the available data are often temporally incomplete - even for high-risk portfolios. In this paper, we prese…

Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards
Ting Yang, Li Chen, Huimin Wang
https://arxiv.org/abs/2508.12935

Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards
Emotional Support Conversation (ESC) systems aim to alleviate users' emotional difficulties and provide long-term, systematic support for emotional well-being. However, most large language model (LLM)-based ESC systems rely on predefined strategies, which limits their effectiveness in complex, real-life scenarios. To enable flexible responses to diverse emotional problem scenarios, this paper introduces a novel end-to-end framework (RLFF-ESC) that directly learns enduring emotionally supportive…

Development of 1-D non-ideal MHD simulation code towards understanding Long-term Evolution of Protoplanetary Disk
Yudai Kobayashi, Daisuke Takaishi, Yusuke Tsukamoto, Shantanu Basu
https://arxiv.org/abs/2508.06089

Development of 1-D non-ideal MHD simulation code towards understanding Long-term Evolution of Protoplanetary Disk
We developed a one-dimensional magnetohydrodynamic (MHD) simulation code to investigate the long-term evolution of protoplanetary disks with low computational cost. In this simulation code, the physical processes necessary for protostellar formation and protoplanetary disk evolution, such as magnetic braking, non-ideal MHD effects, and angular momentum transport due to viscosity, are implemented. Using this simulation code, we performed the simulations of the long-term evolution of protoplaneta…

AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions
Tianjiao Zhao, Jingrao Lyu, Stokes Jones, Harrison Garber, Stefano Pasquali, Dhagash Mehta
https://arxiv.org/abs/2508.11152

AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions
The field of artificial intelligence (AI) agents is evolving rapidly, driven by the capabilities of Large Language Models (LLMs) to autonomously perform and refine tasks with human-like efficiency and adaptability. In this context, multi-agent collaboration has emerged as a promising approach, enabling multiple AI agents to work together to solve complex challenges. This study investigates the application of role-based multi-agent systems to support stock selection in equity research and portfo…

I'm really torn. I love me my @…, great people, great model, love to support and use.
Buuuuut, I'd also love to use my own domain so I can truly own my own social. However I’m concerned about a single user instance not seeing all my current interactions.
Any advice from you self-hosters? I'm trying out

Fedihost - Managed Fediverse Hosting
Fedihost is a managed fediverse hosting service. With a couple of clicks you can be up and running with your own Mastodon or Peertube instance.

Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection
Tairan Huang, Yili Wang
https://arxiv.org/abs/2507.11997 https://

Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection
Graph fraud detection has garnered significant attention as Graph Neural Networks (GNNs) have proven effective in modeling complex relationships within multimodal data. However, existing graph fraud detection methods typically use preprocessed node embeddings and predefined graph structures to reveal fraudsters, which ignore the rich semantic cues contained in raw textual information. Although Large Language Models (LLMs) exhibit powerful capabilities in processing textual information, it remai…

Human-in-the-Loop Systems for Adaptive Learning Using Generative AI
Bhavishya Tarun, Haoze Du, Dinesh Kannan, Edward F. Gehringer
https://arxiv.org/abs/2508.11062 https://

Human-in-the-Loop Systems for Adaptive Learning Using Generative AI
A Human-in-the-Loop (HITL) approach leverages generative AI to enhance personalized learning by directly integrating student feedback into AI-generated solutions. Students critique and modify AI responses using predefined feedback tags, fostering deeper engagement and understanding. This empowers students to actively shape their learning, with AI serving as an adaptive partner. The system uses a tagging technique and prompt engineering to personalize content, informing a Retrieval-Augmented Gen…

Computational Methods and Verification Theorem for Portfolio-Consumption Optimization under Exponential O-U Dynamics
Zhaoxiang Zhong, Haiming Song
https://arxiv.org/abs/2508.06491

Computational Methods and Verification Theorem for Portfolio-Consumption Optimization under Exponential O-U Dynamics
In this paper, we focus on the problem of optimal portfolio-consumption policies in a multi-asset financial market, where the n risky assets follow Exponential Ornstein-Uhlenbeck processes, along with one risk-free bond. The investor's preferences are modeled using Constant Relative Risk Aversion utility with state-dependent stochastic discounting. The problem can be formulated as a high-dimensional stochastic optimal control problem, wherein the associated value function satisfies a Hamilton-J…