The fluctuation of the average construction labour price is one of the important factors that could impact the profits of the construction project. The average construction labour price fluctuation could be affected by various factors. However, if the cost estimation is not defined certainly, it will cause overbudgeting on the operating costs.
Artificial Intelligence is often used in graphics recognition, speech recognition, and other areas. It is often used for forecasting, such as using the Convolutional Neural Network. it is often used to extract features from multi-dimensional data and retain the data to perform image recognition to get higher accuracy than human judgment. There some research has been done to forecast the price fluctuations. For instance, develop the data handling by determining the numerous parameters (e.g., price of steel, oil price, inflation rate, etc.) to forecast the iron ore price. In addition, the movement price of the stock market also can be accurately predicted from multiple time scale features. However, most of the research does not consider the current situation that could affect the forecasting price prediction.
Since there is no actual statistical value data to indicate actual incidents, this thesis uses Convolutional Neural Network to combine the primary factors with relevant events keywords or popular keywords that provided Google Search. It genuinely can represent unquantifiable data. This thesis analyzes the interval time for six months later, three months later, and one month later.
The result of forecasting six months later is higher than 88%, the results of forecasting three months later are higher than 85%, and the results of forecasting one month later are higher than 86%. However, after inputting the related events keyword, the accuracy of results has improved for forecasting six months later. It shows that contractors can use this method to forecast the average construction labour price to help contractors identify the price prediction more accurately when formulating procurement strategies for the cost estimation.

[1] Alexander Malanichev (2011). “Forecast of Global Steel Prices, Studies on Russian Economic Development” 22(3):304-311, DOI: 10.1134/S1075700711030105.
[2] Alexander Pustov, Alexander Malanichev, Ilya Khobotilov, “Long-term iron ore price modeling: Marginal costs vs. incentive price”, Resources Policy Volume 38, Issue 4: Pages 558-567, 2013.
[3] Ashok Kumar S, Santhosh V, Saranyadevi S, Vikranth Krishna E (2020). “Prediction of Job Applicant Salary and Designation using Machine Learning”, International Journal of Innovative Technology and Exploring Engineering (IJITEE). ISSN: 2278-3075, Volume-9 Issue-6
[4] Dartanyon Shivers, Chris Deotte (2017), “Exploring the Relationship between Google Trends Data and Stock Price Data”, Retrieved June 2017, from http://www.ccom.ucsd.edu/~cdeotte/papers/GoogleTrends.pdf
[5] Diyuan Li, Reza Moghadda, Masoud Monjezi, Jahed Armaghani, and Amirhossein Mehrdanesh (2020). “Development of a Group Method of Data Handling Technique to Forecast Iron Ore Price”, Appl. Sci. 2020, 10(7), 2364: https://www.mdpi.com/2076-3417/10/7/2364
[6] Guangyu Jiang (2018). “The Prediction of Aluminum Demand Based on S-shaped Regularity and Research on Supply Proposal of China”, DOI: https://doi.org/10.2991/iceep-18.2018.239
[7] Iain M. Cockburn, Rebecca Henderson & Scott Stern (2018) “The Impact of Artificial Intelligence on Innovation: An Exploratory Analysis”, The Wall Street Journal, DOI 10.3386/w24449
[8] Jessica Gallant, Kory Kroft, Fabian Lange, Matthew J (2020). “Temporary Unemployment and Labor Market Dynamics during The COVID-19 Recession”, National Bureau of Economic Research: https://www.nber.org/papers/w27924
[9] Mohammad Reza Moghaddam, Massod Manjezi, Amir Hossein Mehr Danesh and Gholamhassan Kakha (2014). “Prediction of Monthly Price of Iron Ore by Using Artificial Neural Network”, Indian J.Sci.Res. 7 (1): 1200-1204, 2014.
[10] N Mekras (2017), “Using Artificial Neural Networks to Model Aluminum based Sheet Forming Processes and Tool Details”, J. Phys.: Conf. Ser. 896 012090.
[11] Naccarato, Alessia & Falorsi, Stefano & Loriga, Silvia & Pierini, Andrea (2018), "Combining official and Google Trends data to forecast the Italian youth unemployment rate," Technological Forecasting and Social Change, Elsevier, vol. 130(C), pages 114-122. DOI: 10.1016/j.techfore.2017.11.022.
[12] Phuwadol Samphaongoen (2009). “A Visual Approach to Construction Cost Estimating”, Paper 28. http://epublications.marquette.edu/theses_open/28
[13] Renjie Wang, Wei Pan, Yuehan Li (2019). “Artificial Intelligence in Reproductive Medicine”, Reproduction (Cambridge, England) 158(4). DOI:10.1530/REP-18-0523
[14] S. Paisitkriangkrai, J. Sherrah, P. Janney and A. Van-Den Hengel (2015), "Effective semantic pixel labelling with convolutional networks and Conditional Random Fields," 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2015, pp. 36-43, doi: 10.1109/CVPRW.2015.7301381.
[15] Salisu Afees A, Ogbonna Ahamuefula E, Adewunyi Adeolu (2020). “Google Trends and the Predictability of Precious Metal”, Resources Policy, Elsevier, vol. 65(C). DOI: 10.1016/j.resourpol.2019.101542.
[16] Saman Zia (2017). “RGB-D Object Recognition Using Deep Convolutional Neural Networks”, IEEE International Conference on Computer Vision Workshop (ICCVW). DOI:10.1109/ICCVW.2017.109.
[17] Senem Sahan Vahaplar (2009), “The Importance of Process Modelling and a Case Study Using Idef0”, Cilt/Vol.:10-Sayı/No: 2 : 615-626.
[18] Sheng Chen, Hongxiang (2018), “Stock Prediction Using Convolurional Neural Network”, IOP Conf. Ser.: Mater. Sci. Eng. 435 012026.
[19] Shuang Gao (2016). “A New Approach for Crude Oil Price Prediction based on Steam Learning”, DOI:10.1016/j.gsf.2016.08.002.
[20] Suveka, V., and Shanmuga Priya, T (2017). "Prediction of material price using prediction tools- a comparision." International Journal of Scientific & EngineerigResearch8 (2017): 160-164.
[21] Yamashita, R., Nishio, M., Do, R.K.G (2018) et al. Convolutional neural networks: an overview and application in radiology. Insights Imaging 9, 611–629. DOI: https://doi.org/10.1007/s13244-018-0639-9.
[22] Yaping Hao, Qiang Gao (2020). “Predicting the Trend of Stock Market Index Using Hybrid Neural Network Based on Multiple Time Scale Feature Learning”, Beihang University.: Appl. Sci. 2020, 10(11), 3961. DOI: https://doi.org/10.3390/app10113961
[23] Yasser Elfahham (2019). “Estimation and Prediction of Construction Cost Index using Neural Networks, Time Series and Regression”, DOI:10.1016/j.aej.2019.05.002.
[24] Yiqun Ma and Junhao Wang (2019). “Co-movement between oil, gas, coal, and iron ore prices, the Australian dollar, and the Chinese RMB exchange rates: A coula approach”, Resources Policy, vol. 63, DOI: 10.1016/j.resourpol.2019.101471.
[25] Yuquan Chen, Hongxing Wang, Jie Shen, Xingwei Zhang, and Xiaowei Gao (2021), “Big Data, Scientific Programming, and Industrial Internet of Things” DOI: https://doi.org/10.1155/2021/9976209
[26] Zijie J. Wang (2020). “CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization”, IEEE Transactions on Visualization and Computer Graphics (TVCG).
[27] Activation Functions in Deep Learning, Retrieved October 2017, from understanding-activation-functions-in-deep-learning/
[28] David Orban. Retrieved November 2017, from https://davidorban.com/2017/11/democratizing-access-to-artificial-intelligence/
[29] Economics Online, Micro-Economics, Market Equilibrium, Retrieved from 2020, https://www.economicsonline.co.uk/Competitive_markets/Market_equilibrium.html
[30] Google AI Blog. Retrieved January 2017, from https://ai.googleblog.com/2017/01/the-google-brain-team-looking-back-on.html
[31] International Trade Administration : Global Steel Trade Monitor, Retrieved 2019, from https://www.industry.gov.au/sites/default/files/adc/public-record/505-044c_-_non_confidential_attachment_3-_trade_imports-taiwan.pdf
[32] Lee Jacobson, Retrieved December 2013, from https://www.theprojectspot.com/tutorial-post/introduction-to-artificial-neural-networks-part-1/7
[33] National Taxation Bureau of the Northern Area, Ministry of Finance. Retrieved 2009, from https://www.ntbna.gov.tw/eng
[34] Programmer Sought, TensorFlow Foundation Design Ideas and Programming Model, Retrieved 2018 from https://www.programmersought.com/article/82911073439/
[35] Python-Module Matplotlib, Retrieved January 2014, from https://itom.bitbucket.io/v1-1-0/docs/08_scriptLanguage/pymod-matplotlib.html
[36] Web Scraping to Extract Contact Information, Retrieved October 2018, from web-scraping-to-extract-contact-information-part-1-mailing-lists-854e8a8844d2
[37] 江怡萱 (2020). “Hybridizing Deep Learning with Google Trends to Predict Rebar Price Fluctuation in Taiwan”, DOI：10.6844/NCKU202002541
[38] 王勝榮 (2019). “A Study of Applying Convolutional Neural Networks to Taiwan Rebar Price Fluctuation Prediction”