Revenue forecast models using hybrid intelligent methods

Topaloğlu, Gizem; Kalaycı, Tolga Ahmet; Pekel, Kaan; Akay, Mehmet Fatih

doi:10.2478/ijmce-2024-0009

Abstract

The aim of this study is to forecast the revenue of a seller taking part in an online e-commerce marketplace by using hybrid intelligent methods to help the seller build a solid financial plan. For this purpose, three different approaches are applied in order to accurately forecast the revenue. In the first approach, after applying simple preprocessing steps on the dataset, forecast models are developed with Random Forest (RF). In the second approach, Isolation Forest (IF) is used to detect outliers on the dataset, and minimum Redundancy Maximum Relevance (mRMR) is utilized to select the features that affect the quality of revenue forecast, correctly. In the last approach, a feature selection process is performed first and then the Density-Based Spatial Clustering and Application with Noise (DBSCAN) is used to cluster the dataset. After these processes are carried out, forecast models are developed with RF. The dataset used includes the daily revenue of a seller with several other features. Mean Absolute Percent Error (MAPE) is used for evaluating the performance of the forecast models.

References

Chen X., Cho T., Dou Y., Lev B., Predicting future earnings changes using machine learning and detailed financial data, Journal of Accounting Research, 60(2), 467–515, 2022.
Search in Google Scholar Back to article
Chung I.H., Williams D.W., Do M.R., For better or worse? Revenue forecasting with machine learning approaches, Public Performance and Management Review, 45(5), 1133–1154, 2022.
Search in Google Scholar Back to article
Kureljusic M., Reisch L., Revenue forecasting for European capital market-oriented firms: a comparative prediction study between financial analysts and machine learning models, Corporate Ownership and Control, 19(2), 159–178, 2022.
Search in Google Scholar Back to article
Lin Y., Li B., Moiser T.M., Griffel L.M., Mahalik M.R., Kwon J., Alam S.M.S., Revenue prediction for integrated renewable energy and energy storage system using machine learning techniques, Journal of Energy Storage, 50, 104123, 2022.
Search in Google Scholar Back to article
Mousa G.A., Elamir E.A.H., Hussainey K., Using machine learning methods to predict financial performance: Does disclosure tone matter?, International Journal of Disclosure and Governance, 19, 93–112, 2022.
Search in Google Scholar Back to article
Wasserbacher H., Spindler M., Machine learning for financial forecasting, planning and analysis: Recent developments and pitfalls, arXiv:2107.04851, 2021.
Search in Google Scholar Back to article
Ndikum P., Machine learning algorithms for financial asset price forecasting, arXiv:2004.01504, 2020.
Search in Google Scholar Back to article
Allen J., Giacoman K., Analytical approaches to macroeconomic forecasting: a study of profits through machine learning and deep learning, https://digital.wpi.edu/pdfviewer/nc580q60t, Accessed: January 1, 2020.
Search in Google Scholar Back to article
Piispanen N., Sundqvist R., Vuotila R., Matilainen V., Emerging Technology Adoption and Use, Chapter: Applications of Deep Learning in Finance, ISBN: 978-952-03-1572-6, 1–181, 2020.
Search in Google Scholar Back to article
Huang C.H., Hsieh S.H., Predicting BIM labor cost with random forest and simple linear regression, Automation in Construction, 118(103280), 1–16, 2020.
Search in Google Scholar Back to article
Papadimitriou A., Patel U., Kim L., Bang G., Nematzadeh A., Liu X., A multi-faceted approach to large scale financial forecasting, Proceedings of the First ACM International Conference on AI in Finance, 15–16 October 2020, New York, USA, 5, 1–8, 2020.
Search in Google Scholar Back to article
Weytjens H., Lohmann E., Kleinsteuber M., Cash flow prediction: MLP and LSTM compared to ARIMA and Prophet, Electronic Commerce Research, 21, 371–391, 2021.
Search in Google Scholar Back to article
Rayhan M., Sultana S., Majid A., Financial factors analysis for acquisition premium and anticipation using extreme gradient boosting and deep recurrent neural network, B.Sc. Thesis, Brac University, Dhaka/Bangladesh, 1–58, 2019.
Search in Google Scholar Back to article
Lorenz T., Homburg C., Determinants of analysts’ revenue forecast accuracy, Review of Quantitative Finance and Accounting, 51, 389–431, 2018.
Search in Google Scholar Back to article
Ding Y., Song X., Zen Y., Forecasting financial condition of Chinese listed companies based on support vector machine, Expert Systems with Applications, 34(4), 3081–3089, 2008.
Search in Google Scholar Back to article
Cheng Z., Zou C., Dong J., Outlier detection using isolation forest and local outlier factor, Proceedings of the Conference on Research in Adaptive and Convergent Systems, 24–27 September 2019, Chongqing, China, 161–168, 2019.
Search in Google Scholar Back to article
Ding C., Peng H., Minimum redundancy feature selection from microarray gene expression data, Journal of Bioinformatics and Computational Biology, 03(02), 185–205, 2005.
Search in Google Scholar Back to article
Kumar K.M., Reddy A.R.M., A fast DBSCAN clustering algorithm by accelerating neighbor searching using Groups method, Pattern Recognition, 58, 39–48, 2016.
Search in Google Scholar Back to article
Xu R., Improvements to random forest methodology, Ph.D. Thesis, Iowa State University, Lowa/USA, 1–87, 2013.
Search in Google Scholar Back to article

Revenue forecast models using hybrid intelligent methods

Abstract

Paradigm

My account