Rebar, also known as Reinforcement steel bars is one of the most widely used materials in the construction industry around the world, it is a component of the essential elements of construction like columns, beams, and foundations. Rebar is utilized in almost every type of civil engineering project from buildings, houses, highways, dams, etc. It is an extremely important material in civil engineering owing to its excellent mechanical properties and it is used to provide resistance to support design loads. However, there is an important issue related to it, its price is highly unpredictable since it depends on many factors. This volatility is the reason why contractors are unable to forecast future prices using only their experience or traditional statistical methods. Convolutional Neural Networks (CNN) which is a type of deep learning has proved to be suitable for making similar predictions, in previous research, this methodology has been used to predict stock market prices and construction risks. In this thesis, a list of factors that play a leading role to influence the rebar price in the Honduras market was determined and processed to be used as input data, followed by the development of different CNN architectures to predict the fluctuations of rebar to compare them. The models were designed to make predictions for which will be the price fluctuation percentage for four different time periods, one, three, six, and twelve months ahead in the future of a specific date, using data from the last twelve months of that date. The results showed a highly accurate model using an architecture with dropout layers that outperformed the rest of architectures and it can be used for contractors to execute predictions and be aware of future price changes and be prepare for this kind of fluctuation and develop a buying rebar strategy.

A.G. Malanichev, p. v. (2011). Forecast of Global Steel Prices. Studies on Russian Economic Development, 304-3011.
Alexander Pustov, A. M. (2013). Long-term iron ore price modeling: Marginal costs vs. incentive price. Resources Policy, 558-567.
Al-Hammad, I. A. (2006). Treatment of Reinforcing Steel Bars Prices Fluctuations . Journal King Sand University, 43-63.
Amine B. Khalifa, H. F. (2016). Multiple Instance Fuzzy Inference Neural Networks. Journal of Institute of Electrical and Electronics Engineers, 29-58.
Andrea Cerasa, D. B. (2019). A hedonic model of import steel prices: Is the EU market integrated? Resources Policy, 241-249.
Anwar Ul Haq, A. Z. (2021). Forecasting daily stock trend using multi-filter feature selection and deep learning. Expert systems with applications, 1-8.
Chieng-Chung Nieh, H.-Y. Y.-K. (2013). Cointegration and causal relationships among steel prices of Mainland China, Taiwan , and USA in the presence of multiple structural changes. Empir Econ, 545-561.
Drachal, K. (2019). Forecasting prices of selected metals with Bayesian data-rich models. Resources Policy, 1-16.
Ehsan Hoseinzade, S. H. (2019). CNNpred: CNN-based stock market prediction using a diverse set of variables. Expert Systems With Applications, 273-285.
Elfahham, Y. (2019). Estimation and prediction of construction cost index using neural networks, time series, and regression. Alexandria Engineering Journal, 499-506.
George Hall, J. R. (2021). Estimation of endogenously sampled time series: The case of commodity price speculation in the steel market. Journal of Econometrics, 219-243.
Glauner, P. O. (2015). Deep Convolutional Neural Networks for Smile Recognition. Thesis from Imperial College London - Department of Computing, 1-61.
Gul Polat, D. A. (2006). Economics of on-site vs. off-site fabrication of rebar. Construction Management and Economics , 1185-1198.
Guo Sui, L. H. (2019). Steel product prices transmission activities in the midstream industrial chain and global markets. Resources Policy, 56-71.
Jan Arnold, S. M. (2009). Raw material procurement with fluctuating prices. Internatonal Journal of Production Economics, 353-364.
Jianbai Huang, J. T. (2020). The effect of investors’ information search behaviors on rebar market return dynamics using high frequency data. Resources Policy , 11-25.
Kamruzzaman, A. (2019). Developing Deep Leaning Models to simulate Human Declarative Episodic Memory Storage. International Journal of Advanced Computer Science and Applications, 6-15.
Kilian, L. (2019). Measuring global real economic activity: Do recent critiques hold up to scrutiny? Economics letters, 106-110.
Min-Koo Kim, J. P. (2020). Automated rebar diameter classification using point cloud data based. Automation in Construction, 34-48.
Model fittings. (2021, February 12). Retrieved from cinnamonaitaiwan.medium.com: https://cinnamonaitaiwan.medium.com/cnn%E5%85%A5%E9%96%80-overfitting-d10acd15ec21
Mohammad Reza Moghaddam, M. M. (2014). Prediction of monthly price of iron ore by using artificial Neural Network. Indian J. Sci. Res , 1200-1204.
Salvatore Carta, A. F. (2021). Multi-DQN: An ensemble of Deep Q-learning agents for stock market forecasting. Expert Systems With Applications, 1-16.
Shaolong Sun, S. W. (2020). A new ensemble deep learning approach for exchange rates forecasting and trading. Advanced Engineering Informatics , 20-30.
Shuai Zhang, Y. C. (2021). A novel ensemble deep learning model with dynamic error correction and multi-objective ensemble pruning for time series forecasting. Information Sciences, 427-445.
Sui Guo, H. L. (2019). Steel product prices transmission activities in the midstream industrial chain and global markets. Resources Policy, 56-71.
Tariku Nigussie, M. C. (2020). Influence of rebar practice in the total cost of building construction projects: The case of Hawassa city, Ethiopia. International Journal of Engineering, Science and Technology, 54-65.
World Steel Association. (2020). Worls Steel in Figures. Brussels, Belgium: World Steel Association.
Yang Li, Y. L. (2020). A deep learning approach for real-time rebar counting on the construction sited based on YOLOv3 detector. Automation in Construction, 36-50.
Yanxin Liu, H. L. (2019). Influence of different factors on prices of upstream, middle and downstream products in China's whole industry chain: Based on adaptive Neural Fuzzy inference system. Resources Policy, 134-142.
Yiqun Ma, J. W. (2019). Co-movement between oil, gas, coal, and iron ore prices, the Australian dollar, and the Chinese RMB exchanges rates: A copula approach. Resources Policy, 10-23.
Yun-Cheng Tsai, J.-H. C.-J. (2016). Predict Forex Trend via Convolutional Neural Networks. Jornal of Ministry of Science and Technology of Taiwan , 1-30.
Zhishuo Liu, Y. W. (2015). Steel Prices Index Prediction in China Based on BP Neural Network . Springer-Verlag Berlin Heidelberg Journal, 603-608.