Tracking the strategic focus of companies through topics in their earnings calls is a key task in financial analysis. However, as industries evolve, traditional topic modeling techniques struggle to dynamically capture emerging topics and their relationships. In this work, we propose an LLM-agent driven approach to discover and retrieve emerging topics from quarterly earnings calls. We propose an LLM-agent to extract topics from documents, structure them into a hierarchical ontology, and establish relationships between new and existing topics through a topic ontology. We demonstrate the use of extracted topics to infer company-level insights and emerging trends over time. We evaluate our approach by measuring ontology coherence, topic evolution accuracy, and its ability to surface emerging financial trends.

In the post-Turing era, evaluating large language models (LLMs) involves assessing generated text based on readers' reactions rather than merely its indistinguishability from human-produced content. This paper explores how LLM-generated text impacts readers' decisions, focusing on both amateur and expert audiences. Our findings indicate that GPT-4 can generate persuasive analyses affecting the decisions of both amateurs and professionals. Furthermore, we evaluate the generated text from the aspects of grammar, convincingness, logical coherence, and usefulness. The results highlight a high correlation between real-world evaluation through audience reactions and the current multi-dimensional evaluators commonly used for generative models. Overall, this paper shows the potential and risk of using generated text to sway human decisions and also points out a new direction for evaluating generated text, i.e., leveraging the reactions and decisions of readers. We release our dataset to assist future research.

Investment Analysis is a cornerstone of the Financial Services industry. The rapid integration of advanced machine learning techniques, particularly Large Language Models (LLMs), offers opportunities to enhance the equity rating process. This paper explores the application of LLMs to generate multi-horizon stock ratings by ingesting diverse datasets. Traditional stock rating methods rely heavily on the expertise of financial analysts, and face several challenges such as data overload, inconsistencies in filings, and delayed reactions to market events. Our study addresses these issues by leveraging LLMs to improve the accuracy and consistency of stock ratings. Additionally, we assess the efficacy of using different data modalities with LLMs for the financial domain. We utilize varied datasets comprising fundamental financial, market, and news data from January 2022 to June 2024, along with GPT-4-32k (v0613) (with a training cutoff in Sep. 2021 to prevent information leakage). Our results show that our benchmark method outperforms traditional stock rating methods when assessed by forward returns, specially when incorporating financial fundamentals. While integrating news data improves short-term performance, substituting detailed news summaries with sentiment scores reduces token use without loss of performance. In many cases, omitting news data entirely enhances performance by reducing bias. Our research shows that LLMs can be leveraged to effectively utilize large amounts of multimodal financial data, as showcased by their effectiveness at the stock rating prediction task. Our work provides a reproducible and efficient framework for generating accurate stock ratings, serving as a cost-effective alternative to traditional methods. Future work will extend to longer timeframes, incorporate diverse data, and utilize newer models for enhanced insights.

The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that leverages the internal hidden states of large language models (LLMs) to generate these concept measures. Specifically, the proposed method learns a concept vector that captures how the LLM internally represents the target concept, then estimates the concept value for text data by projecting the text's LLM hidden states onto the concept vector. Three replication studies demonstrate the method's effectiveness in producing highly valid, consistent, and reproducible text-based measures across various social science research contexts, highlighting its potential as a valuable tool for the research community.

Who's at risk of mass job losses caused by the AI revolution - blue or white collar workers? Most experts agree that artificial intelligence will completely upend the American workforce (there are already signs it's doing so in the tech industry). But there have been conflicting reports about who is more at risk, lower-wage workers or middle-management types. A report by the think-tank McKinsey Global estimated Americans on the lowest wages are up to 14 times more likely to be replaced by AI those on the highest. But a separate JP Morgan report predicted'mass-scale white-collar job realignment' this decade.

In this article, we will talk in-depth about an interactive, human-in-the-loop tool called SEER. SEER helps users who work with such text datasets extract relevant data from them. A user in SEER would highlight examples of text they wish to extract. Positive examples are texts they wish to extract. Negative examples are texts they do not wish to extract.

The typical Australian will change careers five to seven times during their professional lifetime, by some estimates. And this is likely to increase as new technologies automate labor, production is moved abroad, and economic crises unfold. Jobs disappearing is not a new phenomenon--have you seen an elevator operator recently? New technologies also create new jobs, but the skills they require do not always match the old jobs. Successfully moving between jobs requires making the most of your current skills and acquiring new ones, but these transitions can falter if the gap between old and new skills is too large.

The first wave of artificial intelligence (AI) has already replaced humans for repetitive physical tasks like inspecting equipment, manufacturing goods, repairing things, and crunching numbers. That shift started way back with the Industrial Revolution. This gave rise to our current Thinking Economy, where employment and wages are more tied to workers' abilities to process, analyze and interpret information to make decisions and solve problems … Just like the industrial revolution automated physical tasks by decreasing the value of human strength and increasing the value of human cognition, AI is now reshaping the landscape and ushering in a Feeling Economy. What characterizes this emerging economy? Consider, for example, the role of a financial analyst, which seems pretty quantitative and thinking-oriented.

This analysis is a part of our project in the Summer Data Competition 2020 hosted by Fuqua School of Business. I want to send my special thank to my teammates: Yaqiong (Juno) Cao and Xinying (Silvia) Sun, for their great contribution. Are you an analytics master student who is seeking a job and have no idea what the job market looks like, especially during COVID-19? Our project aims to analyze the current online job posting situation that can help students better understand the current job market, find the most suitable job positions, and make the best preparation for these jobs. After integrating the latest data from authorized websites like LinkedIn, Yahoo Finance, and company official websites, we generated some interesting insights from our multi-dimensional analysis.

In the financial sector, a reliable forecast the future financial performance of a company is of great importance for investors' investment decisions. In this paper we compare long-term short-term memory (LSTM) networks to temporal convolution network (TCNs) in the prediction of future earnings per share (EPS). The experimental analysis is based on quarterly financial reporting data and daily stock market returns. For a broad sample of US firms, we find that both LSTMs outperform the naive persistent model with up to 30.0% more accurate predictions, while TCNs achieve and an improvement of 30.8%. Both types of networks are at least as accurate as analysts and exceed them by up to 12.2% (LSTM) and 13.2% (TCN).