nach oben

Erschienen in:

2023 | OriginalPaper | Buchkapitel

Applications of Large Language Models (LLMs) in Business Analytics – Exemplary Use Cases in Data Preparation Tasks

verfasst von : Mehran Nasseri, Patrick Brandtner, Robert Zimmermann, Taha Falatouri, Farzaneh Darbanian, Tobechi Obinwanne

Erschienen in: HCI International 2023 – Late Breaking Papers

Verlag: Springer Nature Switzerland

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

The application of data analytics in management has become a crucial success factor for the modern enterprise. To apply analytical models, appropriately prepared data must be available. Preparing this data can be cumbersome, time-consuming, and error prone. In the current era of Artificial Intelligence (AI), Large Language Models (LLMs) like OpenAI’s ChatGPT offer a promising pathway to support these tasks. However, their potential in enhancing the efficiency and effectiveness of data preparation remains largely unexplored. In this paper, we apply and evaluate the performance of OpenAI’s ChatGPT for data preparation. Based on four real-life use cases we show, that ChatGPT demonstrates high performance in the context of translating text, assigning products to given categories, classifying sentiments of customer reviews, and extracting information from textual requests. The results of our paper indicate that ChatGPT can be a valuable tool for many companies, helping with daily data preparation tasks. We demonstrated that ChatGPT can handle different languages and formats of data and have shown that LLMs can perform multiple tasks with minimal or no fine-tuning, leveraging their pre-trained knowledge and generalization abilities. However, we have also observed that ChatGPT may sometimes produce incorrect outputs, especially when input data is noisy or ambiguous. We have also noticed that ChatGPT may struggle with tasks that require more complex reasoning or domain-specific knowledge. Future research should focus on improving the robustness and reliability of LLMs for data preparation tasks, as well as on developing more efficient and user-friendly ways to deploy and interact with them.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel If You Can’t Beat Them, Join Them: How Text-to-Image Tools Can Be Leveraged in the 3D Modelling Process

Nächstes Kapitel Experimental Comparative Study of Three Models of Convolutional Neural Networks for Emotion Recognition

Nur mit Berechtigung zugänglich

Udokwu, C., Brandtner, P., Darbanian, F., Falatouri, T.: Proposals for addressing research gaps at the intersection of data analytics and supply chain management. J. Adv. Inf. Technol. (2022)

Brandtner, P.: Predictive analytics and intelligent decision support systems in supply chain risk management—research directions for future studies. In: Yang, X.-S., Sherratt, S., Dey, N., Joshi, A. (eds.) Proceedings of Seventh International Congress on Information and Communication Technology, vol. 464. Lecture Notes in Networks and Systems, pp. 549–558. Springer Nature Singapore, Singapore (2023)

Brandtner, P., Mates, M.: Artificial intelligence in strategic foresight – current practices and future application potentials. In: Proceedings of the 2021 12th International Conference on E-business, Management and Economics (ICEME 2021). International Conference on E-business, Management and Economics (ICEME 2021), pp. 75–81 (2021)

Zimmermann, R., Auinger, A.: Developing a conversion rate optimization framework for digital retailers—case study. J Market Anal. (2023). https://doi.org/10.1057/s41270-022-00161-y

Fan, X., Wang, X., Zhang, X., ASCE Xiong Yu, P.: Machine learning based water pipe failure prediction: The effects of engineering, geology, climate and socio-economic factors. Reliab. Eng. Syst. Saf. 219, 108185 (2022). https://doi.org/10.1016/j.ress.2021.108185

Schröer, C., Kruse, F., Gómez, J.M.: A Systematic literature review on applying CRISP-DM process model. Procedia Comput. Sci. 181, 526–534 (2021). https://doi.org/10.1016/j.procs.2021.01.199CrossRef

Saltz, J.S.: CRISP-DM for data science: strengths, weaknesses and potential next steps. In: 2021 IEEE International Conference on Big Data (Big Data). 2021 IEEE International Conference on Big Data (Big Data), Orlando, FL, USA, 15.12.2021 – 18.12.2021, pp. 2337–2344. IEEE (2021). https://doi.org/10.1109/BigData52589.2021.9671634

Kung, T.H., et al.: Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLOS Digit. Health 2, e0000198 (2023). https://doi.org/10.1371/journal.pdig.0000198CrossRef

Kosinski, M.: Theory of Mind May Have Spontaneously Emerged in Large Language Models (2023)

10.

Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2019). https://doi.org/10.18653/v1/N19-1423

11.

Leippold, M.: Thus spoke GPT-3: interviewing a large-language model on climate finance. Finance Res. Lett. (2023). https://doi.org/10.1016/j.frl.2022.103617

12.

Brown, T.B., et al.: Language Models are Few-Shot Learners. https://arxiv.org/pdf/2005.14165 (2020)

13.

Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners, 1–9 (2019)

14.

Vaswani, A., et al.: Attention Is All You Need. Advances in neural information processing systems 5998–6008

15.

Liu, Y., et al.: RoBERTa: A Robustly Optimized BERT Pre-training Approach. https://arxiv.org/pdf/1907.11692 (2019)

16.

Raffel, C., et al.: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. http://arxiv.org/pdf/1910.10683v3 (2019)

17.

OpenAI: GPT-4 Technical Report. https://arxiv.org/pdf/2303.08774 (2023)

18.

Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large Language Models are Zero-Shot Reasoners. https://arxiv.org/pdf/2205.11916 (2022)

19.

Ouyang, L., et al.: Training language models to follow instructions with human feedback

20.

Zhang, S., et al.: OPT: Open Pre-trained Transformer Language Models (2022). Accessed 23 Mar 2023

21.

Chakrabarty, T., Padmakumar, V., He, H.: Help me write a poem: instruction tuning as a vehicle for collaborative poetry writing. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 6848–6863

22.

Mahlow, C.: Large Language Models and Artificial Intelligence, the End of (Language) Learning as we Know it—or not quite? https://osf.io/da2rm/download (2023)

23.

Ruder, S., Vulić, I., Søgaard, A.: A survey of cross-lingual word embedding models. JAIR 65, 569–631 (2019). https://doi.org/10.1613/jair.1.11640MathSciNetCrossRefMATH

24.

Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation. http://arxiv.org/pdf/2001.08210v2 (2020)

25.

Snæbjarnarson, V., Einarsson, H.: Cross-lingual QA as a stepping stone for monolingual open QA in Icelandic. In: MIA 2022 - Workshop on Multi-lingual Information Access, Proceedings of the Workshop, pp. 29–36 (2022)

26.

Daull, X., Bellot, P., Bruno, E., Martin, V., Murisasco, E.: Complex QA and language models hybrid architectures, Survey (2023)

27.

DeRosa, D.M., Lepsinger, R.: Virtual Team Success: A Practical Guide for Working and Learning from Distance. John Wiley & Sons

28.

Hosseini-Asl, E., Asadi, S., Asemi, A., Lavangani, M.A.Z.: Neural text generation for idea generation: the case of brainstorming. Int. J. Human-Comput. Stud. 151 (2021)

29.

Palomaki, J., Kytola, A., Vatanen, T.: Collaborative idea generation with a language model. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pp. 1–12 (2021)

30.

Chang, C.K., Huang, Y.M., Hsiao, Y.P., Huang, Y.M.: Exploring the feasibility and acceptance of using a natural language generation system for brain-storming Interactive Learning Environments, 738–751 (2020)

31.

Valvoda, J., Fang, Y., Vandyke, D.: Prompting for a conversation: How to control a dialog model? https://aclanthology.org/2022.cai-1.1.pdf (2022)

32.

Zeng, Y., Nie, J.-Y.: Open-domain dialogue generation based on pre-trained language models (2020)

33.

Li, D., You, J., Funakoshi, K., Okumura, M.: A-TIP: Attribute-aware Text Infilling via Pre-trained Language Model. https://aclanthology.org/2022.coling-1.511.pdf (2022)

34.

Rahali, A., Akhloufi, M.A.: End-to-end transformer-based models in textual-based NLP. AI 4(1), 54–110 (2023). https://doi.org/10.3390/ai4010004CrossRef

35.

Ziegler, D.M., et al.: Fine-Tuning Language Models from Human Preferences. https://arxiv.org/pdf/1909.08593.pdf%5D (2019)

36.

Jiang, X., Liang, Y., Chen, W., Duan, N.: XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledge. https://arxiv.org/pdf/2109.12573 (2021)

37.

Dunn, A., et al.: Structured information extraction from complex scientific text with fi-ne-tuned large language models (2022)

38.

Wu, T., Shiri, F., Kang, J., Qi, G., Haffari, G., Li, Y.-F.: KC-GEE: Knowledge-based Conditioning for Generative Event Extraction (2022)

39.

Santosh, T.Y.S.S., Chakraborty, P., Dutta, S., Sanyal, D.K., Das, P.P.: Joint Entity and Relation Extraction from Scientific Documents: Role of Linguistic Information and Entity Types. https://ceur-ws.org/Vol-3004/paper2.pdf (2021)

40.

Fan, A., Lewis, M., Dauphin, Y.N.: Strategies for training large transformer models (2019)

41.

Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)

42.

Zhang, J., Zhao, Y., Saleh, M., Liu, P.J.: PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization. https://arxiv.org/pdf/1912.08777 (2019)

43.

Zhang, Y., Feng, Y., Chen, Y., Zhao, D.: Conversational language generation: a review (2021)

44.

Zhang, Y., et al.: DIALOGPT: large-scale generative pre-training for conversational response generation. In: Celikyilmaz, A., Wen, T.-H. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, Online, pp. 270–278. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-demos.30

45.

Gao, T., Xia, L., Yu, D. (eds.): Fine-tuning pre-trained language model with multi-level adaptive learning rates for answer selection. In: The 28th International Joint Conference on Artificial Intelligence (2019)

46.

Fu, T., Gao, S., Zhao, X., Wen, J., Yan, R.: Learning towards conversational AI: a survey. AI Open (2022). https://doi.org/10.1016/j.aiopen.2022.02.001

47.

Serban, I.V., Sordoni, A., Bengio, Y., Courville, A., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models. https://arxiv.org/pdf/1507.04808 (2015)

48.

Zhang, J., Yang, H.: Neural response generation with dynamically weighted copy mechanism (2020)

49.

Keskar, N.S., McCann, B., Varshney, L.R., Xiong, C., Socher, R.: CTRL: A Conditional Transformer Language Model for Controllable Generation. http://arxiv.org/pdf/1909.05858v2 (2019)

50.

Hai, H.N.: ChatGPT: The Evolution of Natural Language Processing (2023)

51.

Dou, Z., Li, C., Li, Y., Wang, S.: Improving information extraction via fine-tuning pre-trained language model 39(4), 5371–5381 (2020)

52.

Gao, J., Zhao, H., Yu, C., Xu, R.: Exploring the Feasibility of ChatGPT for Event Extraction. https://arxiv.org/pdf/2303.03836 (2023)

53.

API Reference. https://platform.openai.com/docs/api-reference/introduction. Accessed 3 Apr 2023

54.

Wang, L., et al.: Document-Level Ma-chine Translation with Large Language Models (2023)

55.

Jiao, W., Huang, J., Wang, W., Wang, X., Shi, S., Tu, Z.: ParroT: Translating During Chat Using Large Language Models (2023)

56.

Takahashi, K., Yamamoto, K., Kuchiba, A., Koyama, T.: Confidence interval for micro-averaged F1 and macro-averaged F1 scores. Appl. Intell. 52(5), 4961–4972 (2022). https://doi.org/10.1007/s10489-021-02635-5CrossRef

57.

Yan, L., et al.: Practical and Ethical Challenges of Large Language Models in Education: A Systematic Literature Review (2023)

58.

Reiss, M.V.: Testing the Reliability of ChatGPT for Text Annotation and Classification: A Cautionary Remark (2023)

59.

Wang, Z., Xie, Q., Ding, Z., Feng, Y., Xia, R.: Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study (2023)

60.

Wei, X., et al.: Zero-Shot Information Extraction via Chatting with ChatGPT (2023)

61.

Han, R., Peng, T., Yang, C., Wang, B., Liu, L., Wan, X.: Is Information Extraction Solved by ChatGPT? An Analysis of Performance, Evaluation Criteria, Robustness and Errors (2023)

Titel: Applications of Large Language Models (LLMs) in Business Analytics – Exemplary Use Cases in Data Preparation Tasks
verfasst von: Mehran Nasseri
Patrick Brandtner
Robert Zimmermann
Taha Falatouri
Farzaneh Darbanian
Tobechi Obinwanne
Verlag: Springer Nature Switzerland
Buch: HCI International 2023 – Late Breaking Papers
Print ISBN: 978-3-031-48056-0

Electronic ISBN: 978-3-031-48057-7

Copyright-Jahr: 2023
DOI: https://doi.org/10.1007/978-3-031-48057-7_12