What is Iran's Pickaxe Mountain? Crude oil and natural gas supplies have been disrupted worldwide by the United States-Israel war on Iran, but one energy sector appears to be cashing in - coal. This week, South Africa's thermal coal producer Thungela Resources said it had doubled its half-year profits as the war has forced more countries to buy the fuel. Mining it causes water pollution, and burning it releases enormous amounts of carbon into the atmosphere, which contributes to global warming. In recent months, several countries, especially in Asia, have reversed or delayed promises to scale back on coal production.

Long-term borrowing costs across some of the word's biggest economies hit fresh highs because of concerns over inflation, government debt levels and spending on Artificial Intelligence (AI). The interest rate on US borrowing over 30 years hit 5.33% on Tuesday, the highest since June 2007, meanwhile UK long-term debt reached 5.85%. There were similar moves in Germany and Japan. Interest rates on bonds - which are a type of debt - are known as yields and can directly affect the borrowing costs consumers pay on mortgages, car loans and credit cards. Rising oil prices are the main driver behind this recent surge in bond yields, as investors fear inflation could spike again. If that happens, central banks may choose to raise interest rates to cool inflation.

Chevron and Williams are big winners in the race to power artificial intelligence as they build out gas-fired power plants and pipelines. It's been a banner year for oil and gas companies. Some of the world's biggest oil giants have announced billions of dollars in quarterly profits over the past two weeks, boosted largely by the soaring price of oil thanks to the conflict in the Middle East. But the artificial intelligence boom is also giving fossil fuel companies a new industry to sell their gas, pipelines, and power plants to: data centers . Two American oil and gas companies, Williams and Chevron, are presenting that demand to investors as a huge win.

A screen displays stock market index data as traders work on the floor at the New York Stock Exchange in New York City on Tuesday. A screen displays stock market index data as traders work on the floor at the New York Stock Exchange in New York City on Tuesday. S&P 500 shot up 1.8% and the main measure of Wall Street's health topped its prior all-time high set a few months ago Tue 4 Aug 2026 16.56 EDTLast modified on Tue 4 Aug 2026 18.03 EDT The US stock market rallied to records on Tuesday as profits kept piling up for companies and as oil prices eased. The S&P 500 shot up 1.8%, and the main measure of Wall Street's health topped its prior all-time high set a couple months ago. The Dow Jones industrial average added 907 points, or 1.7%, to its own record set the day before, while the Nasdaq composite jumped 2.6%.

Oil prices have dropped following a report the US and Iran have reached a deal, subject to President Donald Trump's approval. Axios reported officials had made an agreement over an extended ceasefire on Thursday. It drove the price of a barrel of Brent crude down to a low of $93.36 from a earlier high of $98, before rebounding to about $94. Prices had jumped earlier after the US carried out new attacks on Iran, targeting a military site in Bandar Abbas, a strategic port city. The strikes occurred despite an ongoing ceasefire between Tehran and Washington to allow for talks to end the three-month-long war that has effectively closed the Strait of Hormuz waterway, pushing up global energy costs.

The energy market has faced a significant structural change in the past decade. The global strife for decarbonization is encouraging the use of renewable energy sources, thus affecting the traditional supply-demand pattern, which were historically dominated by fossil fuels like coal, oil, and natural gas [18]. The growing integration of renewable energy sources into the power supply increases uncertainties in the electricity market due to intermittent nature of the sources such as wind or sunshine [57]. The volatility of the generation sources causes high price shocks and regime changes that is compromising to financial stability as well as investment strategies in the power market [58]. Particularly for countries such as Germany, where the larger percentage of electricity is produced by renewable energy sources [37], levels of sunlight and wind impact electricity generation and thus prices. This introduces, in addition to the physical problem of balancing the grid, non-stationarity to most price models, which further adds unreliability to the predictions. Accurate electricity price forecasting is crucial for efficient resource planning, financial risk management, and stabilization of the market, especially with increasing renewable energy penetration, which enables utilities, businesses, and governments to optimize planning and policy maximization while matching demand and supply. The building of an adequate prediction model, which is relatively straightforward and understandable but at the same time can reflect the market complexity and all influence factors engaged in it is not straightforward, and authors have utilized quite broadly three types of model for prediction: statistical/(probability-based) models [12], machine learning/deep learning models [42], and mixed models [30]. Precise forecasting allows the players in the market to make sound monetary policy.

The aim of this thesis is to extend the applications of the Quantile Regression Forest (QRF) algorithm to handle mixed-frequency and longitudinal data. To this end, standard statistical approaches have been exploited to build two novel algorithms: the Mixed- Frequency Quantile Regression Forest (MIDAS-QRF) and the Finite Mixture Quantile Regression Forest (FM-QRF). The MIDAS-QRF combines the flexibility of QRF with the Mixed Data Sampling (MIDAS) approach, enabling non-parametric quantile estimation with variables observed at different frequencies. FM-QRF, on the other hand, extends random effects machine learning algorithms to a QR framework, allowing for conditional quantile estimation in a longitudinal data setting. The contributions of this dissertation lie both methodologically and empirically. Methodologically, the MIDAS-QRF and the FM-QRF represent two novel approaches for handling mixed-frequency and longitudinal data in QR machine learning framework. Empirically, the application of the proposed models in financial risk management and climate-change impact evaluation demonstrates their validity as accurate and flexible models to be applied in complex empirical settings.

Financial markets have experienced significant instabilities in recent years, creating unique challenges for trading and increasing interest in risk-averse strategies. Distributional Reinforcement Learning (RL) algorithms, which model the full distribution of returns rather than just expected values, offer a promising approach to managing market uncertainty. This paper investigates this potential by studying the effectiveness of three distributional RL algorithms for natural gas futures trading and exploring their capacity to develop risk-averse policies. Specifically, we analyze the performance and behavior of Categorical Deep Q-Network (C51), Quantile Regression Deep Q-Network (QR-DQN), and Implicit Quantile Network (IQN). To the best of our knowledge, these algorithms have never been applied in a trading context. These policies are compared against five Machine Learning (ML) baselines, using a detailed dataset provided by Predictive Layer SA, a company supplying ML-based strategies for energy trading. The main contributions of this study are as follows. (1) We demonstrate that distributional RL algorithms significantly outperform classical RL methods, with C51 achieving performance improvement of more than 32\%. (2) We show that training C51 and IQN to maximize CVaR produces risk-sensitive policies with adjustable risk aversion. Specifically, our ablation studies reveal that lower CVaR confidence levels increase risk aversion, while higher levels decrease it, offering flexible risk management options. In contrast, QR-DQN shows less predictable behavior. These findings emphasize the potential of distributional RL for developing adaptable, risk-averse trading strategies in volatile markets.

This paper investigates the enhancement of financial time series forecasting with the use of neural networks through supervised autoencoders (SAE), to improve investment strategy performance. Using the Sharpe and Information Ratios, it specifically examines the impact of noise augmentation and triple barrier labeling on risk-adjusted returns. The study focuses on Bitcoin, Litecoin, and Ethereum as the traded assets from January 1, 2016, to April 30, 2022. Findings indicate that supervised autoencoders, with balanced noise augmentation and bottleneck size, significantly boost strategy effectiveness. However, excessive noise and large bottleneck sizes can impair performance.

This study introduces a novel approach for EUR/USD exchange rate forecasting that integrates deep learning, textual analysis, and particle swarm optimization (PSO). By incorporating online news and analysis texts as qualitative data, the proposed PSO-LSTM model demonstrates superior performance compared to traditional econometric and machine learning models. The research employs advanced text mining techniques, including sentiment analysis using the RoBERTa-Large model and topic modeling with LDA. Empirical findings underscore the significant advantage of incorporating textual data, with the PSO-LSTM model outperforming benchmark models such as SVM, SVR, ARIMA, and GARCH. Ablation experiments reveal the contribution of each textual data category to the overall forecasting performance. The study highlights the transformative potential of artificial intelligence in finance and paves the way for future research in real-time forecasting and the integration of alternative data sources.