Construction projects are managed by site managers who are well versed the project management knowledge areas. These construction managers are visionary, knowledgeableand know-it-alls about their profession. However, around the world, especially in low- income countries, especially Ethiopia, most construction projects by construction companies have failed due to a shortage of construction project managers. They are unfamiliar with financial controls that are applied without considering the company'ssituation or the project's situation. The purpose of this research is to develop a machine- learning model for predicting effective financing methods in construction companies. Thisresearch followed an experimental methodology and used the Anaconda environment, Python programming and Jupyter notebooks. Purposive sampling method was employed for collecting data (for machine-learning techniques) from Amhara National Regional StateJob & Training Bureau and their branches namely Bahir Dar, Chagenie and Jawi Construction enterprise/construction associations. The study used about five machine learning algorithms namely: SVM 93.99%, LR 93.78%, DT 93.58%, KNN 92.75% and NB 91.30%. The result showed that the SVM machine learning algorithm outperformed than the other four machine learning methods. Because SVMs work with categorical data,they work better with high-dimensional data and involve nonlinear transformations.