Dr. Abolghasemi has a multi-disciplinary background in Engineering, Business, Statistics, and Machine Learning. His research interests and expertise lie in time series forecasting, predictive analytics, decision making and machine learning, with applications in supply chain management and renewable energies optimisation. Through his research, Dr. Abolghasemi has consulted for dozens of companies in Australia, Europe, and the Middle East, developing several analytical models to enhance their supply chain networks and analytical capabilities. His research is closely tied to evidence-based analytics for real-world problems. He has published over 40 articles and technical reports and has presented at numerous national and international conferences.
Mahdi is a consultant and a member of the International Institute of Forecasters, the Australian Mathematical Society, and INFORMS. He serves on the editorial board of the International Journal of Forecasting and is a regular reviewer for the International Journal of Production Economics, the International Journal of Production Research, and several international conferences. Dr. Abolghasemi is the founding chair and host of an international scientific podcast, "Forecasting Impact," which reaches audiences in over 120 countries around the world.
Dr. Abolghasemi is a passionate teacher and thought leader in higher education. He has studied and worked on three continents. He dedicates himself to supervising talented young students, aiding them in achieving their goals.
Dr Mahdi Abolghasemi is passionate about applied research, i.e, research with applications in solving real-world problems. Dr Abolghasemi has worked on several industry research projects during his working experience in the industry and academic journey. His research has been used in several sectors including the food and beverage supply chain, renewable energy, automotive, mining and construction industries. Mahdi has developed and optimised several decision-making models that are currently in use by organisations in Australia, Europe, and Middle-East.
Book Chapter: Approximating Solutions to the Knapsack Problem Using the Lagrangian Dual Framework
Keegan, Mitchell and Abolghasemi, Mahdi (2023). Approximating Solutions to the Knapsack Problem Using the Lagrangian Dual Framework. Lecture Notes in Computer Science. (pp. 455-467) Singapore: Springer Nature Singapore. doi: 10.1007/978-981-99-8388-9_37
Journal Article: Book review
Abolghasemi, Mahdi (2023). Book review. International Journal of Forecasting, 39 (4), 1949-1951. doi: 10.1016/j.ijforecast.2022.12.002
Journal Article: Machine learning for satisficing operational decision making: a case study in blood supply chain
Abolghasemi, Mahdi, Abbasi, Babak and HosseiniFard, Zahra (2023). Machine learning for satisficing operational decision making: a case study in blood supply chain. International Journal of Forecasting. doi: 10.1016/j.ijforecast.2023.05.004
Analytics for the Australian Grains Industry (AAGI)
(2023–2027) Grains Research & Development Corporation
Predict and optimise with machine learning
Doctor Philosophy
Forecasting and optimising decisions with machine learing
Master Philosophy
A Review of Quarry Mine Datasets in Queensland
Doctor Philosophy
Predicting and then optimising decisions via deep learning
Predictive analytics and optimisation are two prominent techniques capable of addressing numerous real-world challenges. The "predict and optimise" paradigm refers to real-world problems where we need to first predict the unknown values of a variable and then optimise some decisions. For instance, one might aim to predict product demand to fine-tune production planning, or forecast electricity demand to optimally schedule machine operations. This approach has manifold applications across sectors like finance, retail, manufacturing, and energy. Within this context, predictions serve as inputs to optimisation models. While heightened prediction accuracy often bolsters optimisation, it doesn't always directly lead to enhanced results. The core challenge we seek to address is the seamless integration of these two phases to craft an end-to-end model that is focused on decision optimisation. Throughout this process, you will hone machine and deep learning models that consider final decisions in their forecasting efforts.
Forecasting and optimising decisions via Bayesian optimisation
Probabilistic forecasting associates a probability of occurrence with the predicted values, making it a useful technique for determining decisions based on the level of risk one can take. It is a powerful technique that unlike point forecast gives you a complete view of the future unknown values. In this project, we aim to use Bayesian approaches for probabilistic forecasting to predict the demand for products/services and accordingly determine a better decision whatever that may be, e.g., inventory of product, or optimal allocation of resources. We investigate the association between these two using real-world data.
Time Series Hierarchical Forecasting with integer programming
Hierarchical Forecasting has found many applications in real world. Hierarchical time series refers to a collection of time series that have a natural and structural connection, e.g, time series are gathered across different locations such as sales across different stores and states in a country. Research shows that we can leverage the information on sales in one store in a particular location and use that to forecast the sales for another store. This is known as cross-learning in research. This project aims to use optimisation methods like linear and integer programming in the setting of hierarchical time series, to develop an end-to-end algorithm that is able to forecast the entire series in an optimal way.
Approximating Solutions to the Knapsack Problem Using the Lagrangian Dual Framework
Keegan, Mitchell and Abolghasemi, Mahdi (2023). Approximating Solutions to the Knapsack Problem Using the Lagrangian Dual Framework. Lecture Notes in Computer Science. (pp. 455-467) Singapore: Springer Nature Singapore. doi: 10.1007/978-981-99-8388-9_37
Abolghasemi, Mahdi (2023). Book review. International Journal of Forecasting, 39 (4), 1949-1951. doi: 10.1016/j.ijforecast.2022.12.002
Machine learning for satisficing operational decision making: a case study in blood supply chain
Abolghasemi, Mahdi, Abbasi, Babak and HosseiniFard, Zahra (2023). Machine learning for satisficing operational decision making: a case study in blood supply chain. International Journal of Forecasting. doi: 10.1016/j.ijforecast.2023.05.004
Abolghasemi, Mahdi, Tarr, Garth and Bergmeir, Christoph (2022). Machine learning applications in hierarchical time series forecasting: Investigating the impact of promotions. International Journal of Forecasting. doi: 10.1016/j.ijforecast.2022.07.004
Abolghasemi, Mahdi, Rostami-Tabar, Bahman and Syntetos, Aris (2022). The value of point of sales information in upstream supply chain forecasting: an empirical investigation. International Journal of Production Research, 61 (7), 1-16. doi: 10.1080/00207543.2022.2063086
Model selection in reconciling hierarchical time series
Abolghasemi, Mahdi, Hyndman, Rob J., Spiliotis, Evangelos and Bergmeir, Christoph (2022). Model selection in reconciling hierarchical time series. Machine Learning, 111 (2), 739-789. doi: 10.1007/s10994-021-06126-z
Hierarchical forecast reconciliation with machine learning
Spiliotis, Evangelos, Abolghasemi, Mahdi, Hyndman, Rob J., Petropoulos, Fotios and Assimakopoulos, Vassilios (2021). Hierarchical forecast reconciliation with machine learning. Applied Soft Computing, 112 107756, 107756. doi: 10.1016/j.asoc.2021.107756
Demand forecasting in the presence of systematic events: cases in capturing sales promotions
Abolghasemi, Mahdi, Hurley, Jason, Eshragh, Ali and Fahimnia, Behnam (2020). Demand forecasting in the presence of systematic events: cases in capturing sales promotions. International Journal of Production Economics, 230. doi: 10.1016/j.ijpe.2020.107892
Considering pricing and uncertainty in designing a reverse logistics network
Zamani, Mohsen, Abolghasemi, Mahdi, Hosseini, Seyed Mohammad Seyed and Pishvaee, Mir Saman (2020). Considering pricing and uncertainty in designing a reverse logistics network. International Journal of Industrial and Systems Engineering, 35 (2), 158-182. doi: 10.1504/IJISE.2020.107554
Demand forecasting in supply chain: the impact of demand volatility in the presence of promotion
Abolghasemi, Mahdi, Beh, Eric, Tarr, Garth and Gerlach, Richard (2020). Demand forecasting in supply chain: the impact of demand volatility in the presence of promotion. Computers & Industrial Engineering, 142 106380, 106380. doi: 10.1016/j.cie.2020.106380
Alizadeh, Reza, Lund, Peter D., Beynaghi, Ali, Abolghasemi, Mandi and Maknoon, Reza (2016). An integrated scenario-based robust planning approach for foresight and strategic management with application to energy industry. Technological Forecasting and Social Change, 104, 162-171. doi: 10.1016/j.techfore.2015.11.030
A new approach for supply chain risk management: mapping SCOR into Bayesian network
Abolghasemi, Mahdi, Khodakarami, Vahid and Tehranifard, Hamid (2015). A new approach for supply chain risk management: mapping SCOR into Bayesian network. Journal of Industrial Engineering and Management, 8 (1), 280-302. doi: 10.3926/jiem.1281
A Bayesian framework for strategic management in energy industry
Abolghasemi, Mahdi and Alizadeh, Reza (2014). A Bayesian framework for strategic management in energy industry. International Journal of Science, Engineering and Technology, 3 (11), 1360-1366.
Hamza, M., Abolghasemi, M. and Alvandi, A.O. (2021). Forecasting sales with Bayesian networks: a case study of a supermarket product in the presence of promotions. Modeling and Simulation Conference (MODSIM), Sydney, Australia, 5-10 December 2021. Modelling and Simulation Society of Australia and New Zealand. doi: 10.36334/modsim.2021.M9.hamza
Measuring down stream supply chain performance using Bayesian network
Abolghasemi, Mahdi and Khodakarami, Vahid (2014). Measuring down stream supply chain performance using Bayesian network. 44th International Conference of Computer and Industrial Engineering, Istanbul, Turkey, 14-16 October 2014. Los Angeles, CA, United States: Computers and Industrial Engineering.
Analytics for the Australian Grains Industry (AAGI)
(2023–2027) Grains Research & Development Corporation
Predict and optimise with machine learning
Doctor Philosophy — Principal Advisor
Other advisors:
Forecasting and optimising decisions with machine learing
Master Philosophy — Principal Advisor
Other advisors:
A Review of Quarry Mine Datasets in Queensland
Doctor Philosophy — Associate Advisor
Other advisors:
Note for students: The possible research projects listed on this page may not be comprehensive or up to date. Always feel free to contact the staff for more information, and also with your own research ideas.
Predicting and then optimising decisions via deep learning
Predictive analytics and optimisation are two prominent techniques capable of addressing numerous real-world challenges. The "predict and optimise" paradigm refers to real-world problems where we need to first predict the unknown values of a variable and then optimise some decisions. For instance, one might aim to predict product demand to fine-tune production planning, or forecast electricity demand to optimally schedule machine operations. This approach has manifold applications across sectors like finance, retail, manufacturing, and energy. Within this context, predictions serve as inputs to optimisation models. While heightened prediction accuracy often bolsters optimisation, it doesn't always directly lead to enhanced results. The core challenge we seek to address is the seamless integration of these two phases to craft an end-to-end model that is focused on decision optimisation. Throughout this process, you will hone machine and deep learning models that consider final decisions in their forecasting efforts.
Forecasting and optimising decisions via Bayesian optimisation
Probabilistic forecasting associates a probability of occurrence with the predicted values, making it a useful technique for determining decisions based on the level of risk one can take. It is a powerful technique that unlike point forecast gives you a complete view of the future unknown values. In this project, we aim to use Bayesian approaches for probabilistic forecasting to predict the demand for products/services and accordingly determine a better decision whatever that may be, e.g., inventory of product, or optimal allocation of resources. We investigate the association between these two using real-world data.
Time Series Hierarchical Forecasting with integer programming
Hierarchical Forecasting has found many applications in real world. Hierarchical time series refers to a collection of time series that have a natural and structural connection, e.g, time series are gathered across different locations such as sales across different stores and states in a country. Research shows that we can leverage the information on sales in one store in a particular location and use that to forecast the sales for another store. This is known as cross-learning in research. This project aims to use optimisation methods like linear and integer programming in the setting of hierarchical time series, to develop an end-to-end algorithm that is able to forecast the entire series in an optimal way.
Predicting cyber-attacks using Machine learning
Outlier detection is an important problem in many fields including in time series forecasting. Applications include detecting large spikes in transactions, or security breaches. There are some standard techniques that can be used for the early detection of outliers, e.g. extreme value theory.
This research project explores the application of machine learning techniques in the fields of cybersecurity forecasting and anomaly detection. With the ever-growing sophistication of cyber threats, traditional security measures are often insufficient to protect systems and networks effectively. By leveraging machine learning algorithms, this study aims to develop accurate and efficient models for predicting cyber attacks and identifying anomalous behavior. The project involves analyzing large datasets of historical cybersecurity incidents, extracting relevant features, and training models to recognize patterns indicative of malicious activities. The findings of this research have the potential to enhance proactive cybersecurity measures and bolster defence mechanisms against evolving cyber threats.
Optimisation of frameworks for development and operation of automated sound classification in real-world environmental monitoring
Effective methods for sound classification are widely published, but these works often reference highly curated datasets or are applied to tightly controlled scenarios. Accurate sound classification in real-world environments are confounded by variability in signal-to-noise ratios and variability in the characteristics of noise sources. This work seeks to explore the influence that data representations (i.e. data engineering) and construction of training algorithms may have on the performance of environmental noise classification. An existing classification framework and training dataset are available for the purposes of baselining ‘existing’ performance.
Expected Outcomes
Improved understanding of the influence that algorithms and data representations have on the performance of noise classification problems.
This is an industry-supported project. The interested student will work closely with Advitech.
Suitable for Honours students.