|
on Big Data |
| By: | Anishka Chauhan; Pratham Mayur; Yeshwanth Sai Gokarakonda; Pooriya Jamie; Naman Mehrotra |
| Abstract: | This paper presents price prediction models using Machine Learning algorithms augmented with Superforecasters predictions, aimed at enhancing investment decisions. Five Machine Learning models are built, including Bidirectional LSTM, ARIMA, a combination of CNN and LSTM, GRU, and a model built using LSTM and GRU algorithms. The models are evaluated using the Mean Absolute Error to determine their predictive accuracy. Additionally, the paper suggests incorporating human intelligence by identifying Superforecasters and tracking their predictions to anticipate unpredictable shifts or changes in stock prices . The predictions made by these users can further enhance the accuracy of stock price predictions when combined with Machine Learning and Natural Language Processing techniques. Predicting the price of any commodity can be a significant task but predicting the price of a stock in the stock market deals with much more uncertainty. Recognising the limited knowledge and exposure to stocks among certain investors, this paper proposes price prediction models using Machine Learning algorithms. In this work, five Machine learning models are built using Bidirectional LSTM, ARIMA, a combination of CNN and LSTM, GRU and the last one is built using LSTM and GRU algorithms. Later these models are assessed using MAE scores to find which model is predicting with the highest accuracy. In addition to this, this paper also suggests the use of human intelligence to closely predict the shift in price patterns in the stock market The main goal is to identify Superforecasters and track their predictions to anticipate unpredictable shifts or changes in stock prices. By leveraging the combined power of Machine Learning and the Human Intelligence, predictive accuracy can be significantly increased. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.02236 |
| By: | Stevens, Alexander; Okrent, Abigail M.; Mancino, Lisa |
| Keywords: | Food Consumption/Nutrition/Food Safety |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ags:aaea22:343997 |
| By: | Zheng, Maoyong; Escalante, Cesar L. |
| Keywords: | Agricultural Finance, Farm Management, Agribusiness |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ags:aaea22:343857 |
| By: | Villacis, Alexis H.; Badruddoza, Syed; Mishra, Ashok K. |
| Keywords: | International Development, Research Methods/Statistical Methods, Food Security And Poverty |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ags:aaea22:343542 |
| By: | Mühlbauer, Sabrina (Institute for Employment Research (IAB), Nuremberg, Germany); Weber, Enzo (Institute for Employment Research (IAB), Nuremberg, Germany) |
| Abstract: | "This paper develops a large-scale algorithm-based application to improve the match quality in the labor market. We use comprehensive administrative data on employment biographies in Germany to predict job match quality in terms of job stability and wages. The models are estimated with both machine learning (ML) (i.e., XGBoost) and common statistical methods (i.e., OLS, logit). Compared to the latter approach, we find that XGBoost performs better for pattern recognition, analyzes large amounts of data in an efficient way and minimizes the prediction error in the application. Finally, we combine our results with algorithms that optimize matching probability to provide a ranked list of job recommendations based on individual characteristics for each job seeker. This application could support caseworkers and job seekers in expanding their job search strategy." (Author's abstract, IAB-Doku) ((en)) |
| JEL: | C14 C45 J64 C55 |
| Date: | 2024–07–12 |
| URL: | https://d.repec.org/n?u=RePEc:iab:iabdpa:202409 |
| By: | Yu Cheng; Junjie Guo; Shiqing Long; You Wu; Mengfang Sun; Rong Zhang |
| Abstract: | The innovative GNN-CL model proposed in this paper marks a breakthrough in the field of financial fraud detection by synergistically combining the advantages of graph neural networks (gnn), convolutional neural networks (cnn) and long short-term memory (LSTM) networks. This convergence enables multifaceted analysis of complex transaction patterns, improving detection accuracy and resilience against complex fraudulent activities. A key novelty of this paper is the use of multilayer perceptrons (MLPS) to estimate node similarity, effectively filtering out neighborhood noise that can lead to false positives. This intelligent purification mechanism ensures that only the most relevant information is considered, thereby improving the model's understanding of the network structure. Feature weakening often plagues graph-based models due to the dilution of key signals. In order to further address the challenge of feature weakening, GNN-CL adopts reinforcement learning strategies. By dynamically adjusting the weights assigned to central nodes, it reinforces the importance of these influential entities to retain important clues of fraud even in less informative data. Experimental evaluations on Yelp datasets show that the results highlight the superior performance of GNN-CL compared to existing methods. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.06529 |
| By: | Yupeng Cao; Zhiyuan Yao; Zhi Chen; Zhiyang Deng |
| Abstract: | The integration of Large Language Models (LLMs) into financial analysis has garnered significant attention in the NLP community. This paper presents our solution to IJCAI-2024 FinLLM challenge, investigating the capabilities of LLMs within three critical areas of financial tasks: financial classification, financial text summarization, and single stock trading. We adopted Llama3-8B and Mistral-7B as base models, fine-tuning them through Parameter Efficient Fine-Tuning (PEFT) and Low-Rank Adaptation (LoRA) approaches. To enhance model performance, we combine datasets from task 1 and task 2 for data fusion. Our approach aims to tackle these diverse tasks in a comprehensive and integrated manner, showcasing LLMs' capacity to address diverse and complex financial tasks with improved accuracy and decision-making capabilities. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.01953 |
| By: | Helmut Wasserbacher; Martin Spindler |
| Abstract: | Why do companies choose particular capital structures? A compelling answer to this question remains elusive despite extensive research. In this article, we use double machine learning to examine the heterogeneous causal effect of credit ratings on leverage. Taking advantage of the flexibility of random forests within the double machine learning framework, we model the relationship between variables associated with leverage and credit ratings without imposing strong assumptions about their functional form. This approach also allows for data-driven variable selection from a large set of individual company characteristics, supporting valid causal inference. We report three findings: First, credit ratings causally affect the leverage ratio. Having a rating, as opposed to having none, increases leverage by approximately 7 to 9 percentage points, or 30\% to 40\% relative to the sample mean leverage. However, this result comes with an important caveat, captured in our second finding: the effect is highly heterogeneous and varies depending on the specific rating. For AAA and AA ratings, the effect is negative, reducing leverage by about 5 percentage points. For A and BBB ratings, the effect is approximately zero. From BB ratings onwards, the effect becomes positive, exceeding 10 percentage points. Third, contrary to what the second finding might imply at first glance, the change from no effect to a positive effect does not occur abruptly at the boundary between investment and speculative grade ratings. Rather, it is gradual, taking place across the granular rating notches ("+/-") within the BBB and BB categories. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.18936 |
| By: | Hao Shi; Cuicui Luo; Weili Song; Xinting Zhang; Xiang Ao |
| Abstract: | The variability and low signal-to-noise ratio in financial data, combined with the necessity for interpretability, make the alpha factor mining workflow a crucial component of quantitative investment. Transitioning from early manual extraction to genetic programming, the most advanced approach in this domain currently employs reinforcement learning to mine a set of combination factors with fixed weights. However, the performance of resultant alpha factors exhibits inconsistency, and the inflexibility of fixed factor weights proves insufficient in adapting to the dynamic nature of financial markets. To address this issue, this paper proposes a two-stage formulaic alpha generating framework AlphaForge, for alpha factor mining and factor combination. This framework employs a generative-predictive neural network to generate factors, leveraging the robust spatial exploration capabilities inherent in deep learning while concurrently preserving diversity. The combination model within the framework incorporates the temporal performance of factors for selection and dynamically adjusts the weights assigned to each component alpha factor. Experiments conducted on real-world datasets demonstrate that our proposed model outperforms contemporary benchmarks in formulaic alpha factor mining. Furthermore, our model exhibits a notable enhancement in portfolio returns within the realm of quantitative investment. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.18394 |
| By: | Haibo Han (Lanzhou University of Finance and Economics); Bin Wang (Lanzhou University of Finance and Economics) |
| Abstract: | Employment policy is an important factor affecting the employment level of college graduates. Based on the policy documents of the Ministry of Education and the text data of the annual report on the employment quality of college graduates from 2015 to 2019 this presentation uses the text data analysis method to calculate the policy perception of colleges and universities, and uses the panel regression model to evaluate the policy effect. The study found that the policy perception of colleges and universities often increases gradually with time and the midland is higher than the eastern and western parts of China. In addition, no matter whether control education investment, policy perception can signi |
| Date: | 2024–06–29 |
| URL: | https://d.repec.org/n?u=RePEc:boc:fsug24:35 |
| By: | Kamil Kashif; Robert \'Slepaczuk |
| Abstract: | This study focuses on building an algorithmic investment strategy employing a hybrid approach that combines LSTM and ARIMA models referred to as LSTM-ARIMA. This unique algorithm uses LSTM to produce final predictions but boosts the results of this RNN by adding the residuals obtained from ARIMA predictions among other inputs. The algorithm is tested across three equity indices (S&P 500, FTSE 100, and CAC 40) using daily frequency data from January 2000 to August 2023. The testing architecture is based on the walk-forward procedure for the hyperparameter tunning phase that uses Random Search and backtesting the algorithms. The selection of the optimal model is determined based on adequately selected performance metrics focused on risk-adjusted return measures. We considered two strategies for each algorithm: Long-Only and Long-Short to present the situation of two various groups of investors with different investment policy restrictions. For each strategy and equity index, we compute the performance metrics and visualize the equity curve to identify the best strategy with the highest modified information ratio. The findings conclude that the LSTM-ARIMA algorithm outperforms all the other algorithms across all the equity indices which confirms the strong potential behind hybrid ML-TS (machine learning - time series) models in searching for the optimal algorithmic investment strategies. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.18206 |
| By: | Jinniao Qiu; Antony Ware; Yang Yang |
| Abstract: | This paper is devoted to the price-storage dynamics in natural gas markets. A novel stochastic path-dependent volatility model is introduced with path-dependence in both price volatility and storage increments. Model calibrations are conducted for both the price and storage dynamics. Further, we discuss the pricing problem of discrete-time swing options using the dynamic programming principle, and a deep learning-based method is proposed for numerical approximations. A numerical algorithm is provided, followed by a convergence analysis result for the deep-learning approach. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.16400 |
| By: | Daiya Mita (Nomura Asset Management Co, ltd., Graduate School of Economics, The University of Tokyo); Akihiko Takahashi (Graduate School of Economics, The University of Tokyo) |
| Abstract: | This study proposes a novel equity investment strategy that effectively integrates artificial intelligence (AI) techniques, multi factor models and financial technical indicators. To be practically useful as an investment fund, the strategy is designed to achieve high investment performance without losing interpretability, which is not always the case especially for complex models based on artificial intelligence. Specifically, as an equity long (buying) strategy, this paper extends a five factor model in Fama & French [1], a well-known finance model for its explainability to predict future returns by using a gradient boosting machine (GBM) and a state space model. In addition, an index futures short (selling) strategy for downside hedging is developed with IF-THEN rules and three technical indicators. Combining individual equity long and index futures short models, the strategy invests in high expected return equities when the expected return of the portfolio is positive and also the market is expected to rise, otherwise it shorts (sells) index futures. To the best of our knowledge, the current study is the first attempt to develop an equity investment strategy based on a new predictable five factor model, which becomes successful with effective use of AI techniques and technical indicators. Finally, empirical analysis shows that the proposed strategy outperforms not only the baseline buy-and-hold strategy, but also typical mutual funds for the Japanese equities. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:cfi:fseres:cf588 |
| By: | Daiya Mita (Nomura Asset Mahagement Co., Ltd); Akihiko Takahashi (The University of Tokyo) |
| Abstract: | This study proposes a novel equity investment strategy that effectively integrates artificial intelligence (AI) techniques, multi factor models and financial technical indicators. To be practically useful as an investment fund, the strategy is designed to achieve high investment performance without losing interpretability, which is not always the case especially for complex models based on artificial intelligence. Specifically, as an equity long (buying) strategy, this paper extends a five factor model in Fama & French [1], a well-known finance model for its explainability to predict future returns by using a gradient boosting machine (GBM) and a state space model. In addition, an index futures short (selling) strategy for downside hedging is developed with IF-THEN rules and three technical indicators. Combining individual equity long and index futures short models, the strategy invests in high expected return equities when the expected return of the portfolio is positive and also the market is expected to rise, otherwise it shorts (sells) index futures. To the best of our knowledge, the current study is the first attempt to develop an equity investment strategy based on a new predictable five factor model, which becomes successful with effective use of AI techniques and technical indicators. Finally, empirical analysis shows that the proposed strategy outperforms not only the baseline buy-and-hold strategy, but also typical mutual funds for the Japanese equities. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:tky:fseres:2024cf1230 |
| By: | Enrique Estefania-Salazar; Michael Carter; Eva Iglesias; Álvaro Escribano |
| Abstract: | Despite its promise to help low-wealth households manage climate risk, index insurance remains hampered by downside basis risk, meaning that an insured party suffers a loss, but receives no payment because the insurance index fails to register a loss. While efforts to reduce basis risk focus on the creation of indices that better predict losses, this paper focuses on the creation of statistically rigorous insurance zones that minimize downside basis risk. In contrast to our approach, most existing index insurance contracts use statistically ad hoc administrative boundaries to demarcate insurance zones. To improve on this practice, we develop a machine learning algorithm that forms zones to maximizes lower tail dependence within the zone. After exploring the logic for using lower tail dependence, we apply our algorithm to the long-running index-based livestock insurance contract in Northern Kenya. We show that compared to the currently employed administrative insurance areas, our algorithm creates an insurance contract that increases the expected utility value of the insurance by 60-200% even when keeping the number of zones the same. Optimizing the number of zones using our method can further increase the economic value of index insurance to its beneficiaries. |
| JEL: | G22 O13 O16 |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:32618 |
| By: | Jibang Wu; Siyu Chen; Mengdi Wang; Huazheng Wang; Haifeng Xu |
| Abstract: | The agency problem emerges in today's large scale machine learning tasks, where the learners are unable to direct content creation or enforce data collection. In this work, we propose a theoretical framework for aligning economic interests of different stakeholders in the online learning problems through contract design. The problem, termed \emph{contractual reinforcement learning}, naturally arises from the classic model of Markov decision processes, where a learning principal seeks to optimally influence the agent's action policy for their common interests through a set of payment rules contingent on the realization of next state. For the planning problem, we design an efficient dynamic programming algorithm to determine the optimal contracts against the far-sighted agent. For the learning problem, we introduce a generic design of no-regret learning algorithms to untangle the challenges from robust design of contracts to the balance of exploration and exploitation, reducing the complexity analysis to the construction of efficient search algorithms. For several natural classes of problems, we design tailored search algorithms that provably achieve $\tilde{O}(\sqrt{T})$ regret. We also present an algorithm with $\tilde{O}(T^{2/3})$ for the general problem that improves the existing analysis in online contract design with mild technical assumptions. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.01458 |
| By: | Peng Yifeng; Gao Chen |
| Abstract: | This study proposes an innovative evaluation method based on large language models (LLMs) specifically designed to measure the digital transformation (DT) process of enterprises. By analyzing the annual reports of 4407 companies listed on the New York Stock Exchange and Nasdaq from 2005 to 2022, a comprehensive set of DT indicators was constructed. The findings revealed that DT significantly improves a company's financial performance, however, different digital technologies exhibit varying effects on financial performance. Specifically, blockchain technology has a relatively limited positive impact on financial performance. In addition, this study further discovered that DT can promote the growth of financial performance by enhancing operational efficiency and reducing costs. This study provides a novel DT evaluation tool for the academic community, while also expanding the application scope of generative artificial intelligence technology in economic research. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.18440 |
| By: | Magnus Lundgren |
| Abstract: | This study investigates the efficacy of large language models (LLMs) as tools for grading master-level student essays. Utilizing a sample of 60 essays in political science, the study compares the accuracy of grades suggested by the GPT-4 model with those awarded by university teachers. Results indicate that while GPT-4 aligns with human grading standards on mean scores, it exhibits a risk-averse grading pattern and its interrater reliability with human raters is low. Furthermore, modifications in the grading instructions (prompt engineering) do not significantly alter AI performance, suggesting that GPT-4 primarily assesses generic essay characteristics such as language quality rather than adapting to nuanced grading criteria. These findings contribute to the understanding of AI's potential and limitations in higher education, highlighting the need for further development to enhance its adaptability and sensitivity to specific educational assessment requirements. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.16510 |
| By: | Matilde Cappelletti; Leonardo M. Giuffrida; Leonardo Maria Giuffrida |
| Abstract: | A set-aside promotes a more equitable procurement process by restricting participation in government tenders to small or disadvantaged businesses. Yet its micro-effects on tender outcomes (competition and contract efficiency) and targeted firm performance entail trade-offs, which we evaluate empirically using a decade of US federal procurement data. At the tender level, we employ a two-stage approach. First, we use random forest techniques to compute the propensity score for a tender being set aside based on rules implementation. Second, we employ the scores in an inverse probability weighting framework. We find that set-asides prompt more competition—implying that the rise in participation of targeted firms more than offsets the exclusion of untargeted ones—and inefficiency, measured by cost overruns and delays. We argue that adverse selection and moral hazard are mechanisms behind contract inefficiency. We then study the targeted firm behavior to uncover whether long-run benefits mitigate short-run drawbacks. We compare businesses differentially exposed to a set-aside spending shock through an event study framework. We find mixed evidence on firm growth. |
| Keywords: | set-aside program, public procurement, firm dynamics, random forest, propensity score, event study |
| JEL: | H32 H57 L25 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ces:ceswps:_11142 |
| By: | Ecker-Ehrhardt, Matthias |
| Abstract: | Communication professionals working for International Organizations (IOs) are important intermediaries of global governance that increasingly use social media to reach out to citizens directly. Social media pose new challenges for IO public communication, such as a highly competitive economy of attention and the fragmentation of audiences driven by networked curation of content and selective exposure. In this context, IO social media communication has to make tough choices about what to communicate and how, aggravating inherent conflicts of IO communication between comprehensive public information (aiming at institutional transparency) - and partisan political advocacy (aiming at normative change). If IOs choose advocacy, they might garner substantial resonance on social media. IO advocacy nevertheless fails to the extent that it fosters the polarized fragmentation of networked communication and undermines the credibility of IO communication as a source of trust - worthy information across polarized 'echo chambers'. The paper illustrates this argument through a quantitative content and social network analysis of X/Twitter communication on the Global Compact for Safe, Orderly, and Regular Migration (GCM). Remarkably, instead of facilitating cross-cluster communication ('building bridges'), United Nations accounts seem to have substantially fostered ideological fragmentation ('digging the trench') by their way of partisan retweeting, mentioning, and (hash)tagging. |
| Keywords: | international organizations, social media, public communication, echo chambers, advocacy, United Nations, Global Compact for Migration, content analysis, supervised machine learning, social network analysis |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:khkgcr:300240 |
| By: | Cai, Xiqian (Xiamen University); Chen, Shuai (University of Leicester); Cheng, Zhengquan (Xiamen University) |
| Abstract: | Gender inequality and discrimination still persist, even though the gender gap in the labor market has been gradually decreasing. This study examines the effect of the #MeToo movement on judges' gender gap in their vital labor market outcome–judicial decisions on randomly assigned legal cases in China. We apply a difference-in-differences approach to unique verdict data including rich textual information on characteristics of cases and judges, and compare changes in sentences of judges of a different gender after the movement. We find that female judges made more severe decisions post-movement, which almost closed the gender gap. Moreover, we explore a potential mechanism of gender norms, documenting evidence for improved awareness of gender equality among women following the movement and stronger effects on judges' gender gap reduction in regions with better awareness of gender equality. This implies that female judges became willing to stand out and speak up, converging to their male counterparts after the #MeToo movement. |
| Keywords: | #MeToo movement, gender gap, inequality, judicial decision, crime, machine learning |
| JEL: | J16 K14 O12 P35 D63 |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:iza:izadps:dp17115 |