İNOVASYON YÖNETİMİ ARAŞTIRMALARINA DERİN ÖĞRENME ALGORİTMASI UYGULAMAK MÜMKÜN MÜ?

Year 2023, Issue: 56, 217 - 226, 22.05.2023

Cemal Öztürk , Mustafa İncekara , Sezai Tokat

https://doi.org/10.30794/pausbed.1127776

Abstract

Bu makale, farklı dış finansman faktörlerinin KOBİ'lerin yenilenebilir enerjiyi gibi eko-inovasyon uygulamalarını benimsemesini nasıl etkilediğini açıklamayı amaçlamaktadır. Derin öğrenme algoritması uygulanarak 5456 KOBİ'nin yenilenebilir enerji operasyonlarını benimseme konusunda çeşitli dış finansal girdi değişkenlerinin tahmini incelenmiştir. Yenilenebilir enerjinin benimsenmesine ilişkin farklı girdi değişkenlerinin performansını değerlendirmek için veri kümesine Uzun Kısa Süreli Bellek Modeli (LSTM) uygulanmıştır. Ayrıca veri setini farklı makine öğrenme algoritmaları ile karşılaştırılmıştır. Bulgular, LSTM'nin tüm metrikler için en yüksek performansı verdiğini göstermektedir. Sonuç olarak, bazı önemli teorik çıkarımlar verilmiştir.

Keywords

Yapay Zeka, Makine Öğrenmesi, Derin Öğrenme, LSTM, Eko-inovasyon, Yenilenebilir Enerji

IS IT POSSIBLE TO APPLY A DEEP LEARNING ALGORITHM TO INNOVATION MANAGEMENT RESEARCH?

Abstract

This paper aims to apply a deep learning algorithm to estimate the prediction of various external financial input variables on adopting eco-innovation practices such as renewable energy operations of 5456 SMEs. A Long Short-Term Memory Units (LSTM) is applied to the data set to evaluate the performance of different input variables on the adoption of renewable energy. Furthermore, we process the dataset with different machine learning algorithms and compare the results. The findings indicate that LSTM gives the highest performance for all metrics. As a result, some important theoretical implications for management scholars are given.

Keywords

Artificial Intelligence, Machine Learning, Deep Learning, LSTM, Eco‐innovation, Renewable Energy

References

• Amidi A. and Amidi S. (2018). “Deep Learning cheatsheet", https://stanford.edu/~shervine/teaching/cs-229/cheatsheet-deep-learning (09.02. 2022).
• Amidi A. and Amidi S. (2019). “Recurrent Neural Networks cheatsheet, https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks (09.02. 2022).
• Cevik, F. and Kilimci, Z.H. (2021). “The evaluation of Parkinson's disease with sentiment analysis using deep learning methods and word embedding models”, Pamukkale University Journal of Engineering Sciences, 27(2), 151–161.
• Chalmers, D., MacKenzie, N.G. and Carter, S. (2021). “Artificial Intelligence and Entrepreneurship: Implications for Venture Creation in the Fourth Industrial Revolution”, Entrepreneurship Theory and Practice, 45(5), 1028–1053.
• European Commission (2016). Flash Eurobarometer 441 (European SMEs and the Circular Economy. Brussels DG Communication COMM A1 “Strategy, Corporate Communication Actions and Eurobarometer”.
• Hochreiter S. and Schmidhuber J. (1997). Long short-term memory, Neural Computation, 9(8), 1735-1780.
• Lévesque, M., Obschonka, M., Nambisan, S., 2020. “Pursuing Impactful Entrepreneurship Research Using Artificial Intelligence”, Entrepreneurship Theory and Practice, 104225872092736.
• Obschonka, M., Audretsch, D.B., 2020. “Artificial intelligence and big data in entrepreneurship: a new era has begun”, Small Business Economics, 55(3), 529–539.
• Özkaya, U., Seyfi, L. and Öztürk, Ş. (2021). “Dimension optimization of multi-band microstrip antennas using deep learning methods”, Pamukkale University Journal of Engineering Sciences, 27(2), 229–233.
• Tonidandel, Scott; King, Eden B.; Cortina, Jose M. (2018). “Big Data Methods”, Organizational Research Methods 21 (3), pp. 525–547.
• Townsend, David M.; Hunt, Richard A. (2019). “Entrepreneurial action, creativity, and judgment in the age of artificial intelligence”, Journal of Business Venturing Insights 11, e00126.