nep-ain New Economics Papers
on Artificial Intelligence
Issue of 2023‒10‒02
eight papers chosen by
Ben Greiner, Wirtschaftsuniversität Wien

  1. Assessing the Impact of Artificial Intelligence on Germany's Labor Market: Insights from a ChatGPT Analysis By Oschinski, Matthias
  2. The Impact of Artificial Intelligence on Economic Patterns By Lohani, Fazle; Rahman, Mostafizur; Shaturaev, Jakhongir
  3. AI Watch: Adoption of Autonomous Machines By CARBALLA SMICHOWSKI Bruno; DE NIGRIS Sarah; DUCH BROWN Nestor; MORENO MARÍA Adrián
  4. Transportation by the Hand of a Ghost: The Influence of Trait Anxiety in the Context of Fear of giving up Control on the Acceptance of Autonomous Vehicles By Schandl, Franziska; Hudecek, Matthias F. C.
  5. Harnessing the Power of Artificial Intelligence to Forecast Startup Success: An Empirical Evaluation of the SECURE AI Model By Morande, Swapnil; Arshi, Tahseen; Gul, Kanwal; Amini, Mitra
  6. Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance By Lefteris Loukas; Ilias Stogiannidis; Prodromos Malakasiotis; Stavros Vassos
  7. Predicting Financial Market Trends using Time Series Analysis and Natural Language Processing By Ali Asgarov
  8. Fairness Implications of Heterogeneous Treatment Effect Estimation with Machine Learning Methods in Policy-making By Patrick Rehill; Nicholas Biddle

  1. By: Oschinski, Matthias
    Abstract: We assess the impact of artificial intelligence (AI) on Germany’s labour market applying the methodology on suitability for machine learning (SML) scores established by Brynjolfsson et al., (2018). However, this study introduces two innovative approaches to the conventional methodology. Instead of relying on traditional crowdsourcing platforms for obtaining ratings on automatability, this research exploits the chatbot capabilities of OpenAI's ChatGPT. Additionally, in alignment with the focus on the German labor market, the study extends the application of SML scores to the European Classification of Skills, Competences, Qualifications and Occupations (ESCO). As such, a distinctive contribution of this study lies in the assessment of ChatGPT's effectiveness in gauging the automatability of skills and competencies within the evolving landscape of AI. Furthermore, the study enhances the applicability of its findings by directly mapping SML scores to the European ESCO classification, rendering the results more pertinent for labor market analyses within the European Union. Initial findings indicate a measured impact of AI on a majority of the 13, 312 distinct ESCO skills and competencies examined. A more detailed analysis reveals that AI exhibits a more pronounced influence on tasks related to computer utilization and information processing. Activities involving decision-making, communication, research, collaboration, and specific technical proficiencies related to medical care, food preparation, construction, and precision equipment operation receive relatively lower scores. Notably, the study highlights the comparative advantage of human employees in transversal skills like creative thinking, collaboration, leadership, the application of general knowledge, attitudes, values, and specific manual and physical skills. Applying our rankings to German labour force data at the 2-digit ISCO level suggests that, in contrast to previous waves of automation, AI may also impact non-routine cognitive occupations. In fact, our results show that business and administration professionals as well as science and engineering associate professionals receive relatively higher rankings compared to teaching professionals, health associate professionals and personal service workers. Ultimately, the research underscores that the overall ramifications of AI on the labor force will be contingent upon the underlying motivations for its deployment. If the primary impetus is cost reduction, AI implementation might follow historical patterns of employment losses with limited gains in productivity. As such, public policy has an important role to play in recalibrating incentives to prioritize machine usefulness over machine intelligence.
    Keywords: Generative AI, Labour, Skills Suitability for Machine Learning, German labour market, ESCO
    JEL: A1 J0
    Date: 2023–08–14
  2. By: Lohani, Fazle; Rahman, Mostafizur; Shaturaev, Jakhongir
    Abstract: This article discusses five specific economic patterns influenced by AI: the emergence of the machina economica, the acceleration of the division of labor, the introduction of AI leading to triangular agency relationships, the recognition of data and AI-based machine labor as new factors of production, and the potential for market dominance and unintended external effects. This analysis is grounded in institutional economics and aims to integrate findings from relevant disciplines in economics and computer science. It is based on the research finding that institutional matters remain highly relevant in a world with AI, but AI introduces a new dimension to these matters. The discussion reveals a reinforcing interdependence among the patterns discussed and highlights the need for further research.
    Keywords: AI; labor classifications; methodological procedure; agent-principal conflict; economics of scale
    JEL: D0 F1 F16 G0
    Date: 2023–01–10
  3. By: CARBALLA SMICHOWSKI Bruno (European Commission - JRC); DE NIGRIS Sarah (European Commission - JRC); DUCH BROWN Nestor (European Commission - JRC); MORENO MARÍA Adrián
    Abstract: This report provides an empirical analysis of the drivers of and barriers to adoption of autonomous machines (AM) technologies by European companies. It also analyses the impact of adopting this technology on firm productivity. Using 2020 survey data from 9 640 firms located in EU27, Norway, Iceland and the UK, we show that AM adoption is driven by several factors and has heterogeneous effects on companies depending on their characteristics. Regarding the drivers of adoption, we find that firm size, employee knowledge of artificial intelligence (AI) and the joint adoption of AM with complementary technologies increase a firm’s probability of adopting AM. Concerning barriers to adoption, we make three main findings. First, the most relevant barriers (cost of adoption and, to a lesser extent, lack of skills and data access) are different for large firms. For the latter, liability and reputation risks, as well as data access, are the most important obstacles. Second, certain types of obstacles (namely liability and reputation risks, data access and lack of funding) are more likely to be present in certain sectors of activity. Third, the more complementary technologies a firm adopts, the lower its probability of facing obstacles to AM adoption. Finally, we find that AM adoption boosts firm productivity. This effect is higher for firms that start out with lower productivity, which suggests that there is a decreasing marginal return to AM adoption in terms of productivity.
    Date: 2023–08
  4. By: Schandl, Franziska (Regensburg University); Hudecek, Matthias F. C.
    Abstract: Autonomous driving has gained increasing attention in recent years and is already beginning to make its first steps into our daily road traffic [2, 3]. Pilot projects are underway worldwide in which artificial intelligence (AI) replaces humans as drivers. In just a few years, autonomous vehicles (AVs) are expected to account for 50 % of new vehicles [4]. In this wake, a huge research field has opened around autonomous driving. In recent years, in addition to technical feasibility, the focus has increasingly been on factors that contribute to humans' successful adoption of AVs. The person of the user with his or her individual perception and personality is a crucial adjusting screw for the successful establishment of AVs. In this context, potential uncertainties, worries, and fears regarding new, largely unknown technologies such as AVs also play an important role [5]. The degree of anxiety with which a person encounters AVs can be crucial for the ultimate use and success of this development [6]. Although findings on the positive relationship between anxiety and AV acceptance have been confirmed, results are still inconsistent. Recent findings even suggest that high trait anxiety has a positive effect on AV acceptance [7]. One possible explanation for this finding is that the more anxious people are, the more they value the possibility of giving up control in AVs. However, this assumption has not yet been examined. To better understand anxiety as an essential factor for the acceptance of autonomous vehicles, we investigate in this study the relationship between trait anxiety and acceptance in the context of fear of giving up control. We also focus on to whom control is handed over: the driver in the normal bus or the AI in the autonomous bus. With our findings, we aim to contribute to the successful establishment of AVs.
    Date: 2023–08–25
  5. By: Morande, Swapnil; Arshi, Tahseen; Gul, Kanwal; Amini, Mitra
    Abstract: This pioneering study employs machine learning to predict startup success, addressing the long-standing challenge of deciphering entrepreneurial outcomes amidst uncertainty. Integrating the multidimensional SECURE framework for holistic opportunity evaluation with AI's pattern recognition prowess, the research puts forth a novel analytics-enabled approach to illuminate success determinants. Rigorously constructed predictive models demonstrate remarkable accuracy in forecasting success likelihood, validated through comprehensive statistical analysis. The findings reveal AI’s immense potential in bringing evidence-based objectivity to the complex process of opportunity assessment. On the theoretical front, the research enriches entrepreneurship literature by bridging the knowledge gap at the intersection of structured evaluation tools and data science. On the practical front, it empowers entrepreneurs with an analytical compass for decision-making and helps investors make prudent funding choices. The study also informs policymakers to optimize conditions for entrepreneurship. Overall, it lays the foundation for a new frontier of AI-enabled, data-driven entrepreneurship research and practice. However, acknowledging AI’s limitations, the synthesis underscores the persistent relevance of human creativity alongside data-backed insights. With high predictive performance and multifaceted implications, the SECURE-AI model represents a significant stride toward an analytics-empowered paradigm in entrepreneurship management.
    Date: 2023–08–29
  6. By: Lefteris Loukas; Ilias Stogiannidis; Prodromos Malakasiotis; Stavros Vassos
    Abstract: We propose the use of conversational GPT models for easy and quick few-shot text classification in the financial domain using the Banking77 dataset. Our approach involves in-context learning with GPT-3.5 and GPT-4, which minimizes the technical expertise required and eliminates the need for expensive GPU computing while yielding quick and accurate results. Additionally, we fine-tune other pre-trained, masked language models with SetFit, a recent contrastive learning technique, to achieve state-of-the-art results both in full-data and few-shot settings. Our findings show that querying GPT-3.5 and GPT-4 can outperform fine-tuned, non-generative models even with fewer examples. However, subscription fees associated with these solutions may be considered costly for small organizations. Lastly, we find that generative models perform better on the given task when shown representative samples selected by a human expert rather than when shown random ones. We conclude that a) our proposed methods offer a practical solution for few-shot tasks in datasets with limited label availability, and b) our state-of-the-art results can inspire future work in the area.
    Date: 2023–08
  7. By: Ali Asgarov
    Abstract: Forecasting financial market trends through time series analysis and natural language processing poses a complex and demanding undertaking, owing to the numerous variables that can influence stock prices. These variables encompass a spectrum of economic and political occurrences, as well as prevailing public attitudes. Recent research has indicated that the expression of public sentiments on social media platforms such as Twitter may have a noteworthy impact on the determination of stock prices. The objective of this study was to assess the viability of Twitter sentiments as a tool for predicting stock prices of major corporations such as Tesla, Apple. Our study has revealed a robust association between the emotions conveyed in tweets and fluctuations in stock prices. Our findings indicate that positivity, negativity, and subjectivity are the primary determinants of fluctuations in stock prices. The data was analyzed utilizing the Long-Short Term Memory neural network (LSTM) model, which is currently recognized as the leading methodology for predicting stock prices by incorporating Twitter sentiments and historical stock prices data. The models utilized in our study demonstrated a high degree of reliability and yielded precise outcomes for the designated corporations. In summary, this research emphasizes the significance of incorporating public opinions into the prediction of stock prices. The application of Time Series Analysis and Natural Language Processing methodologies can yield significant scientific findings regarding financial market patterns, thereby facilitating informed decision-making among investors. The results of our study indicate that the utilization of Twitter sentiments can serve as a potent instrument for forecasting stock prices, and ought to be factored in when formulating investment strategies.
    Date: 2023–08
  8. By: Patrick Rehill; Nicholas Biddle
    Abstract: Causal machine learning methods which flexibly generate heterogeneous treatment effect estimates could be very useful tools for governments trying to make and implement policy. However, as the critical artificial intelligence literature has shown, governments must be very careful of unintended consequences when using machine learning models. One way to try and protect against unintended bad outcomes is with AI Fairness methods which seek to create machine learning models where sensitive variables like race or gender do not influence outcomes. In this paper we argue that standard AI Fairness approaches developed for predictive machine learning are not suitable for all causal machine learning applications because causal machine learning generally (at least so far) uses modelling to inform a human who is the ultimate decision-maker while AI Fairness approaches assume a model that is making decisions directly. We define these scenarios as indirect and direct decision-making respectively and suggest that policy-making is best seen as a joint decision where the causal machine learning model usually only has indirect power. We lay out a definition of fairness for this scenario - a model that provides the information a decision-maker needs to accurately make a value judgement about just policy outcomes - and argue that the complexity of causal machine learning models can make this difficult to achieve. The solution here is not traditional AI Fairness adjustments, but careful modelling and awareness of some of the decision-making biases that these methods might encourage which we describe.
    Date: 2023–09

This nep-ain issue is ©2023 by Ben Greiner. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.