Publications

Accurate cost estimating is required to improve decision making based on project economic evaluations. The process of cost estimation largely depends on some attributes such as scope definitions and project schedule. On the other hand, the strong database is required to predict the cost based on historical and future market rates. One of the solutions is using probabilistic model to have range of possible outcome for an estimate. Recently, computing techniques such as data analytics and machine learning for quick and accurate cost estimation has been seen as an alternative to overcome the uncertainty of input parameters. Fuzzy Logic Concept which leverages statistical approach, nonlinear equations and genetic algorithm programming is used to model the cost. Fuzzy Logic resembles the human decision-making methodology. The metrics are used to supply meaningful and timely management information regarding techniques and process. Cost Estimate Relationship (CER) is established to model the correlation against the technical deliverables at any stage gate process to support the target metrics. This paper presents an alternative method to estimate the cost which is applied to offshore platforms and wells through machine learning as it compares the performance of three different machine learning algorithms: Simple Linear Regression (baseline model), Ridge regression and Support Vector Regression (SVR). Performance of the algorithm is measured by the RMSE value, which in this case the predicted platform cost by the model against the actual cost observed. The results show that despite the limitation in the amount of data, the algorithms exhibit high performance with both Simple Linear Regression and Ridge Regression recording average error or deviation of platform cost of RM 14.3 million and SVR recording RM 3.5 million deviation, which is the lowest RMSE value. The fuzzy logic algorithm used in predicting the costs have returned fairly accurate results when compared to actual cost generated using conventional method.