THE INFLUENCER PRICING PROGNOSTICATION ON SOCIAL MEDIA DYNAMICS AN ADVANCED EXAMINATION OF LINEAR REGRESSION 2 POLY DEGREE ALGORITHM & NEURAL NETWORK AN ADVANCED EXAMINATION OF LINEAR REGRESSION 2 POLY DEGREE ALGORITHM & NEURAL NETWORK
Abstract
The pervasive influence of social media has spawned the influencer profession, a potent force shaping audience interest in promoted products and services. Unlike traditional media, the impact of influencer promotion is quantifiable, with rates typically determined by factors such as follower count, engagement, and reach. However, the absence of a standardized reference for rate determination poses a potential risk of losses for both influencers and clients. This study seeks to address this challenge through the development of an advanced machine learning-based deep learning predictive model, incorporating Linear Regression with a second-degree polynomial algorithm and a neural network to enhance accuracy. This research underscores the potential of machine learning, including advanced regression algorithms and neural networks, in providing a robust framework for predicting influencer rates. The developed model serves as a significant step toward minimizing adverse effects on both influencers and clients by offering a more nuanced and accurate reference for rate determination in the dynamic landscape of social media promotion The Model Evaluation based on Mean Absolute Error (MAE) metrics reveals that the Keras Neural Network outperformed both Simple Linear Regression (10.612) and Linear Regression with a 2nd-degree polynomial (10.089) in predicting influencer rates. With a substantially lower MAE of 7.952, the neural network demonstrated superior accuracy, leveraging its capacity to capture intricate data relationships and learn non-linear patterns. In conclusion, the Keras Neural Network emerges as the most effective model for influencer rate prediction.
References
Agustian, K., Hidayat, R., Zen, A., Sekarini, R. A., & Malik, A. J. (2023). The Influence of Influencer Marketing in Increasing Brand Awareness and Sales for SMEs. Technology and Society Perspectives (TACIT), 1(2), 68–78. https://doi.org/10.61100/tacit.v1i2.54
Atiq, M., Abid, G., Anwar, A., & Ijaz, M. F. (2022). Influencer Marketing on Instagram: A Sequential Mediation Model of Storytelling Content and Audience Engagement via Relatability and Trust. Information (Switzerland), 13(7). https://doi.org/10.3390/info13070345
Fan, F. L., Xiong, J., Li, M., & Wang, G. (2021). On Interpretability of Artificial Neural Networks: A Survey. IEEE Transactions on Radiation and Plasma Medical Sciences, 5(6), 741–760. https://doi.org/10.1109/TRPMS.2021.3066428
Gerlich, M. (2023). The Power of Virtual Influencers: Impact on Consumer Behaviour and Attitudes in the Age of AI. Administrative Sciences, 13(8). https://doi.org/10.3390/admsci13080178
Guzik, T. J., Mohiddin, S. A., Dimarco, A., Patel, V., Savvatis, K., Marelli-Berg, F. M., Madhur, M. S., Tomaszewski, M., Maffia, P., D’Acquisto, F., Nicklin, S. A., Marian, A. J., Nosalski, R., Murray, E. C., Guzik, B., Berry, C., Touyz, R. M., Kreutz, R., Dao, W. W., … McInnes, I. B. (2020). COVID-19 and the cardiovascular system: Implications for risk assessment, diagnosis, and treatment options. In Cardiovascular Research (Vol. 116, Issue 10, pp. 1666–1687). Oxford University Press. https://doi.org/10.1093/cvr/cvaa106
Kamal, M., & Bablu, T. A. (2022). International Journal of Applied Machine Learning and Computational Intelligence Machine Learning Models for Predicting Click-through Rates on social media: Factors and Performance Analysis. International Journal of Applied Machine Learning and Computational Intelligence, 4(11), 1–14.
Kigo, S. N., Omondi, E. O., & Omolo, B. O. (2023). Assessing predictive performance of supervised machine learning algorithms for a diamond pricing model. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-44326-w
Moubayed, A., Injadat, M., Nassif, A. B., Lutfiyya, H., & Shami, A. (2018). E-Learning: Challenges and Research Opportunities Using Machine Learning Data Analytics. IEEE Access, 6, 39117–39138. https://doi.org/10.1109/ACCESS.2018.2851790
Musiyiwa, R., & Jacobson, J. (2023). Sponsorship Disclosure in Social Media Influencer Marketing: The Algorithmic and Non-Algorithmic Barriers. Social Media and Society, 9(3). https://doi.org/10.1177/20563051231196870
Shah, A., & Nasnodkar, S. (2019). A Framework for Micro-Influencer Selection in Pet Product Marketing Using Social Media Performance Metrics and Natural Language Processing. Journal of Computational Social Dynamics Research Article: Journal of Computational Social Dynamics, 07(01), 7.
Stoldt, R., Wellman, M., Ekdale, B., & Tully, M. (2019). Professionalizing and Profiting: The Rise of Intermediaries in the Social Media Influencer Industry. Social Media and Society, 5(1). https://doi.org/10.1177/2056305119832587
Wang, X., Wang, Y., Tao, F., & Liu, A. (2021). New Paradigm of Data-Driven Smart Customisation through Digital Twin. Journal of Manufacturing Systems, 58, 270–280. https://doi.org/10.1016/j.jmsy.2020.07.023
Authors
Copyright (c) 2024 Felicia Canesta, Rusdianto Roestam
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published workÂ
