Key Words: Risk Factors, Risk Impacts, Model, Artificial Neural Network, Cash Flow Forecast
Area of Research
Cash flow forecasting is a vital contributing factor in construction industry where lead to the high rate of insolvencies. Risks involved with construction industry play significant role for the variation of forecasted and actual cash flow. Identification of risks and risk assessment are important to develop accurate cash flow forecast. Statistical, mathematical and simulation approaches were adapted to the identification of risk impact assessment. Though significant variation is still observed with actual and forecasted cash flow. So …show more content…
Three approaches were used in developing cost profile method; net cash flow, contract value data (value flow) and construction cost data (cost flow or cost commitment) by utilizing the three sides of the cash flow equation. Though significant deviation observed with actual and modeled forecast due to lack of addressing the risks impact inherent with construction industry. So in this paper it is focused to develop a model to predict the changes to baseline of cost flow due to risk occurred during construction stage.
Brief Overview of previous relevant research
There are number of researches carried out in developing model to identify risk factors and the impact to cost flow forecast in construction industry. Henry et al., (2012) in his paper discussed to develop a model to assess the impacts of identified risks to baseline cost flow using regression model. A multiple linear regression model were developed using identified risk factors and the periodic variability measurement.
H.Odeyinka et.al. (2013) uses an artiﬁcial neural network back propagation algorithm to develop a model to identify the risk factors and the impact on cost flow forecast. Though research was unable to address the risk impact to the cost forecast with different project type and procurement …show more content…
At first stage it is planned to use structured questioner to collect data from homogeneous and comprehensive samples for different project types and different procurement method. This data will be used to identify the significant risk factors inherent with the industry. At second stage cash flow forecast and actual cost flow cast will be collected. Then artificial neural network model will be developed to identify risk impacts. This will be followed by five stages 1)data acquisition, analysis and problem representation;(2)architecture determination;(3)learning process determination;(4)training of the network; and(5) testing of the trained Network for generalization evaluation (Ogunlana etal.2001;EzeldinandSharara,2006). Then plan to use simulation techniques to further validate of risk impacts on cost flow forecast. The similar methodology and approach used in H.Odeyinka et.al. (2013) and Henry et al., (2012) will be used in the