Neural Network-Enhanced Decision Support: Investigating Prediction Intervals for Real-Time Digital Marketing Return on Investment Data

• Lucas Rabelo de Araujo Morais UFBA
• Gecynalda Soares da Silva Gomes UFBA

DOI: https://doi.org/10.5753/brasnam.2024.2232

Resumo

This work delves into the application of artificial neural network (ANN) models and recurrent neural networks (RNN), for time-series forecasting in the dynamic realm of digital marketing. Focused on a travel company’s real-time updated Return on Investment (ROI) data from Google Ads campaigns, the research evaluates the efficacy of prediction intervals (PIs) in capturing forecast uncertainties. The study’s contribution lies in the exploration of PIs in ANN models for digital marketing ROI data, providing valuable insights for decision-makers navigating rapidly changing scenarios. The work emphasizes the significance of incorporating intervals in ANN models for robust decision-making in business and digital marketing applications.

Referências

Abiodun, O., Jantan, A., Omolara, A., Dada, K., Mohamed, N., and Arshad, H. (2018). State-of-the-art in artificial neural network applications: A survey. Heliyon, 4(11).

Armstrong, J. (2001). Principles of Forecasting: A Handbook for Researchers and Practitioners.

Botchkarev, A. and Andru, P. (2011). A return on investment as a metric for evaluating information systems: Taxonomy and application. Interdisciplinary Journal of Information, Knowledge, and Management, 6:245–269.

Brezak, D., Bacek, T., Majetic, D., Kasac, J., and Novakovic, B. (2012). A comparison of feed-forward and recurrent neural networks in time series forecasting. In IEEE Conference on Computational Intelligence for Financial Engineering Economics (CIFEr).

Burn, D. and Elnur, M. (2002). Detection of hydrologic trends and variability. Journal Of Hydrology, 255:107–122.

Carney, J., Cunningham, P., and Bhagwan, U. (1999). Confidence and prediction intervals for neural network ensembles. In IJCNN’99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339), volume 2, page 1215–1218 vol.2.

de Araujo Morais, L. R. (Last accessed on January 13, 2024). Relatório dinâmico - voal - otis / dynamic report - voal - otis. Author’s personal website. [link] (In Portuguese).

de Sousa, A., Furtado, H., Macêdo, W., and Meneses, A. (2020). Analysis of artificial neural network point forecasting models and prediction intervals for solar irradiance estimation. American Journal of Engineering and Applied Sciences, 13(3):347–357. DOI: 10.3844/ajeassp.2020.347.357.

Goerg, G. (2013). Forecastable component analysis (foreca). Available from: arXiv:1205.4591 [stat.ME].

Goodwin, P., Önkal, D., and Thomson, M. (2010). Do forecasts expressed as prediction intervals improve production planning decisions? European Journal of Operational Research, 205(1):195–201. DOI: 10.1016/j.ejor.2009.12.020.

Guo, T., Xu, Z., Yao, X., Chen, H., Aberer, K., and Funaya, K. (2016). Robust online time series prediction with recurrent neural networks. page 816–825.

Hyndman, R. and Athanasopoulos, G. (2021). Forecasting: Principles and Practice. OTexts, Melbourne, Australia, 3rd edition.

Järvinen, J. and Karjaluoto, H. (2015). The use of web analytics for digital marketing performance measurement. Industrial Marketing Management, 50:117–127.

Kasiviswanathan, K. and Sudheer, K. (2016). Comparison of methods used for quantifying prediction interval in artificial neural network hydrologic models. Model. Earth Syst. Environ., 22(2).

Lou, H., Wang, X., Gao, Y., and Zeng, Q. (2022). Comparison of arima model, dnn model and lstm model in predicting disease burden of occupational pneumoconiosis in tianjin, china. BMC Public Health, 22:2167. DOI: 10.1186/s12889-022-14642-3.

Mei, L., Hu, R., Cao, H., Liu, Y., Han, Z., and Li, F. e. a. (2019). Realtime mobile bandwidth prediction using lstm neural network. page 34–47.

Morettin, P. and Toloi, C. (2004). Análise de Séries Temporais [Time Series Analysis]. Edgard Blucher.

Nielsen, H. (2005). Non-stationary time series and unit root tests. Accessed January 11, 2024.

Nourani, V., Paknezhad, N., and Tanaka, H. (2021). Prediction interval estimation methods for artificial neural network (ann)-based modeling of the hydro-climatic processes, a review. Sustainability, 13(4).

Quan, H., Srinivasan, D., and Khosravi, A. (2014). Uncertainty handling using neural network-based prediction intervals for electrical load forecasting. Energy, 73:916–925.

Ristow, D., Henning, E., Kalbusch, A., and Petersen, C. (2021). Models for forecasting water demand using time series analysis: a case study in southern brazil. Journal of Water, Sanitation and Hygiene for Development, 11(2):231–240.

Siami-Namini, S., Tavakoli, N., and Siami Namin, A. (2018). A comparison of arima and lstm in forecasting time series. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), page 1394–1401.

Wanjohi, R. (2018). Time series forecasting using lstm in r. Last Access: 11/01/2024. [link].

Wong, B., Bodnovich, T., and Selvi, Y. (1997). Neural network applications in business: A review and analysis of the literature (1988–1995). Decision Support Systems, 19(4):301–320.

Zeroual, A., Harrou, F., Dairi, A., and Sun, Y. (2019). Deep learning methods for forecasting covid-19 time-series data: A comparative study. Chaos, Solitons Fractals, 6(47):110121.

Zhu, L. and Laptev, N. (2017). Deep and confident prediction for time series at uber. In 2017 IEEE International Conference on Data Mining Workshops (ICDMW), page 103–110.