A5044153153- Forecasting Techniques and Applications
- Energy Load and Power Forecasting
- Time Series Analysis and Forecasting
- Financial Risk and Volatility Modeling
- FinTech, Crowdfunding, Digital Finance
- Sustainable Supply Chain Management
- Quality and Supply Management
- Decision-Making and Behavioral Economics
- Banking stability, regulation, efficiency
- Statistical and Computational Modeling
- COVID-19 Pandemic Impacts
- Stock Market Forecasting Methods
- Consumer Retail Behavior Studies
- Market Dynamics and Volatility
- Economic and Environmental Valuation
- Hydrological Forecasting Using AI
- Sharing Economy and Platforms
- Digital Transformation in Industry
- Supply Chain Resilience and Risk Management
Manchester Metropolitan University
2019-2024
Forecasting has always been at the forefront of decision making and planning. The uncertainty that surrounds future is both exciting challenging, with individuals organisations seeking to minimise risks maximise utilities. large number forecasting applications calls for a diverse set methods tackle real-life challenges. This article provides non-systematic review theory practice forecasting. We provide an overview wide range theoretical, state-of-the-art models, methods, principles,...
This paper proposes a novel forecasting method that combines the deep learning – long short-term memory (LSTM) networks and random forest (RF). The proposed can model complex relationships of both temporal regression type which gives it an edge in accuracy over other methods. We evaluated new on real-world multivariate dataset from multi-channel retailer. benchmark performance proposition against neural networks, multiple regression, ARIMAX, LSTM RF. employed metrics to measure bias,...
This research focuses on the impact of 'Industry 4.0ʹ and "Digital Transformation" information sharing decision making across supply chain (SC). Following a qualitative approach, findings are threefold: First, it is shown that possibility an entire SC integration based new technologies still at distance. Current burdens missing willingness to exchange far-reaching even with long-term partners technological interface standards in order enable trouble-free communication alongside SC. Second,...
Due to global warming, flood is an increasing threat companies operating in the pulp and paper industry. The impact of this needs be managed. We deploy a qualitative investigation into how manufacturers can forecast mitigate special events, most notably floods, across their supply chains. A grounded theory approach using semi-structured interviews held with chain consultants three stages allowed for topic categories emerging during previous explored. Analysis these uncovered tactics unique...
Data analysts when forecasting large number of time series, they regularly employ one the following methodological approaches: either select a single method for entire dataset (aggregate selection), or use best each series (individual selection). There is evidence in predictive analytics literature that former more robust than latter, as individual selection you tend to overfit models data. A third approach first identify homogeneous clusters within dataset, and then cluster (cluster To end,...