Maximum Drawdown Research Articles

Analysis of Changes in the Stress–Strain State and Permeability of a Terrigenous Reservoir Based on a Numerical Model of the Near-Well Zone with Casing and Perforation Channels

A finite element model, which includes reservoir rock, cement stone, casing, and perforation channels, was developed. The purpose of the study is to create a geomechanical model of the zone around the well, which includes support elements and perforation channels. This model will help predict changes in the productivity coefficient of a terrigenous reservoir and determine the most efficient mode of operation of a producing well. In order to exclude the stress concentration within the casing–cement stone and cement stone–rock, the numerical model applies contact elements. As a result, structural elements slip, while the stresses are redistributed accurately. The numerical simulation of a stress state in the near-well zone was carried out by using the developed model with differential pressure drawdown on the terrigenous reservoir, one of the oil fields in the Perm region. It is shown that the safety factor of the casing reaches roughly 3–4 units. The only exceptions are the upper and lower parts of the perforations, where this parameter is close to one unit. The safety factor of cement stone accounts for 2–3 units. However, parts with its lowest value (1.35) are also concentrated near the perforation channels. In order to analyze the change in permeability, the dependence of the safety factor on effective stresses was taken into account. Therefore, it was found that, in the upper and lower parts of perforations, the stresses decreased, while permeability rose by up to 20% of the initial value. An increase in differential pressure drawdown, on the contrary, can lead to a permeability reduction of 25%, especially in the lateral parts of the perforations. Areas of rock destruction under tensile and compressive forces were identified by using the Mohr–Coulomb criterion. It is estimated that with an increase in pressure drawdown, the areas of rock destruction under tensile force disappear, while the areas of rock destruction under compression increase. After further analysis, it was found that, with the maximum pressure drawdown of 12 MPa, the well productivity index can decrease by 15% due to the reservoir rock compaction.

Dynamic Black–Litterman Portfolios Incorporating Asymmetric Fractal Uncertainty

This study investigates the profitability of portfolios that integrate asymmetric fractality within the Black–Litterman (BL) framework. It predicts 10-day-ahead exchange-traded fund (ETF) prices using recurrent neural networks (RNNs) based on historical price information and technical indicators; these predictions are utilized as BL views. While constructing the BL portfolio, the Hurst exponent obtained from the asymmetric multifractal detrended fluctuation analysis is employed to determine the uncertainty associated with the views. The Hurst exponent describes the long-range persistence in time-series data, which can also be interpreted as the uncertainty in time-series predictions. Additionally, uncertainty is measured using asymmetric fractality to account for the financial time series’ asymmetric characteristics. Then, backtesting is conducted on portfolios comprising 10 countries’ ETFs, rebalanced on a 10-day basis. While benchmarking to a Markowitz portfolio and the MSCI world index, profitability is assessed using the Sharpe ratio, maximum drawdown, and sub-period analysis. The results reveal that the proposed model enhances the overall portfolio return and demonstrates particularly strong performance during negative trends. Moreover, it identifies ongoing investment opportunities, even in recent periods. These findings underscore the potential of fractality in adjusting uncertainty for diverse portfolio optimization applications.

Visual MODFLOW, solute transport modeling, and remote sensing techniques for adapting aquifer potentiality under reclamation and climate change impacts in coastal aquifer

Global environmental changes, such as climate change and reclamation alterations, significantly influence hydrological processes, leading to hydrologic nonstationarity and challenges in managing water availability and distribution. This study introduces a conceptual underpinning for the rational development and sustainability of groundwater resources. As one of the areas intended for the development projects within the Egyptian national plan for the reclamation of one and a half million acres; hundreds of pumping wells were constructed in the Moghra area to fulfill the reclamation demand. This study investigates the long-term impacts of exploiting the drilled pumping wells under climate change. The approach is to monitor the groundwater levels and the salinity values in the Moghra aquifer with various operational strategies and present proposed sustainable development scenarios. The impact of global warming and climate change is estimated for a prediction period of 30 years by using satellite data, time series geographical analysis, and statistical modeling. Using MODFLOW and Solute Transport (MT3DMS) modules of Visual MODFLOW USGS 2005 software, a three-dimensional (3D) finite-difference model is created to simulate groundwater flow and salinity distribution in the Moghra aquifer with the input of forecast downscaling (2020–2050) of main climatic parameters (PPT, ET, and Temp). The optimal adaptation-integrated scenario to cope with long-term groundwater withdrawal and climate change impacts is achieved when the Ministry of Irrigation and Water Resources (MWRI) recommends that the maximum drawdown shouldn’t be more significant than 1.0 m/ year. In this scenario, 1,500 pumping wells are distributed with an equal space of 500 m, a pumping rate of 1,200 m3/day and input the forecast of the most significant climatic parameters after 30 years. The output results of this scenario revealed a drawdown level of 42 m and a groundwater salinity value of 16,000 mg/l. Climate change has an evident impact on groundwater quantity and quality, particularly in the unconfined coastal aquifer, which is vulnerable to saltwater intrusion and pollution of drinking water resources. The relationship between climate change and the hydrologic cycle is crucial for predicting future water availability and addressing water-related issues.

Bitcoin Return Prediction: Is It Possible via Stock-to-Flow, Metcalfe’s Law, Technical Analysis, or Market Sentiment?

Popular methods to value Bitcoin include the stock-to-flow model, Metcalfe’s Law, technical analysis, and sentiment-related measures. Within this paper, I test whether such models and variables are predictive of Bitcoin’s returns. I find that the stock-to-flow model predictions and Metcalfe’s Law help to explain Bitcoin’s returns in-sample but have limited to no ability to predict Bitcoin’s returns out-of-sample. In contrast, Bitcoin market sentiment and technical analysis measures are generally unrelated to Bitcoin’s returns in-sample and are poor predictors of Bitcoin’s returns out-of-sample. Despite the poor performance of Bitcoin return predictors within out-of-sample regressions, I demonstrate that a very successful out-of-sample Bitcoin tactical allocation or “market timing” strategy is formed via blending out-of-sample univariate model predictions. This OOS-blended model trading strategy, which algorithmically allocates between Bitcoin and cash (USD), significantly outperforms buying-and-holding or “HODL”ing Bitcoin, boosting CAPM alpha by almost 1300 basis points while also increasing portfolio Sharpe Ratio and Sortino Ratio and dramatically reducing portfolio maximum drawdown relative to buying-and-holding Bitcoin.

Deep Reinforcement Learning Approach to Portfolio Optimization in the Australian Stock Market

The future of portfolio management is evolving from relying on human expertise to incorporating artificial intelligence techniques. Traditional techniques such as fundamental and technical analysis will eventually be replaced by more sophisticated deep reinforcement learning (DRL) algorithms. However, it is still a long way from designing a profitable strategy in the complex and dynamic stock market. While previous studies have focused on the American stock market, this paper applies two DRL algorithms, the proximal policy optimization (PPO) and the advantage actor–critic (A2C), to trade the constituent stocks of the Australian Securities Exchange 50 (ASX50) Index. This paper also incorporates a weighted moving average into the action space and introduces a transaction threshold to help agents minimize trivial trades that lead to high transaction costs. The results are presented and benchmarked against the ASX50 Index. The A2C agent was better at following trends and had the higher upside potential but can suffer from more severe damage during bearish markets. On the other hand, the PPO agent had the lowest annual volatility and the highest maximum drawdown, which is more helpful in a bearish or volatile market.

A Stock Market Decision-Making Framework Based on CMR-DQN

In the dynamic and uncertain stock market, precise forecasting and decision-making are crucial for profitability. Traditional deep neural networks (DNN) often struggle with capturing long-term dependencies and multi-scale features in complex financial time series data. To address these challenges, we introduce CMR-DQN, an innovative framework that integrates discrete wavelet transform (DWT) for multi-scale data analysis, temporal convolutional network (TCN) for extracting deep temporal features, and a GRU–LSTM–Attention mechanism to enhance the model’s focus and memory. Additionally, CMR-DQN employs the Rainbow DQN reinforcement learning strategy to learn optimal trading strategies in a simulated environment. CMR-DQN significantly improved the total return rate on six selected stocks, with increases ranging from 20.37% to 55.32%. It also demonstrated substantial improvements over the baseline model in terms of Sharpe ratio and maximum drawdown, indicating increased excess returns per unit of total risk and reduced investment risk. These results underscore the efficiency and effectiveness of CMR-DQN in handling multi-scale time series data and optimizing stock market decisions.

A three-level nested portfolio optimization model with position allocation

Existing portfolio optimization models cannot well capture the real position allocation requirement, leading to limited impact in practice. To overcome this challenge, we propose a three-level nested portfolio optimization model with position allocation. Within this model, the inner and middle levels collaboratively determine the optimal portfolio, while the outer level focuses on optimizing the holding proportion of each stock in the optimal portfolio. Compared with existing models with portfolio weights, the proposed model imposes the position allocation constraint that precisely characterizes the limitations on holding each stock. This constraint is crucial for investors to obey securities trading regulations involving position limitations and to mitigate the potential impact of market risks. To address the nonlinear and nonconvex nature of the novel model, we develop an intelligent optimization algorithm by effectively hybridizing the support vector regression and the enhanced grey wolf optimizer. We comprehensively evaluate its performance using eight metrics, including accumulative return, annual return, Sharpe ratio, maximum drawdown, absolute and relative win ratios, predictive precision and accuracy. The experimental results indicate that (i) the proposed model can achieve more excess returns than those stock selection models not considering position allocation, especially for the large-cap stocks; (ii) compared with other state-of-the-art meta-heuristics, the enhanced grey wolf optimizer can yield better portfolio in conjunction with the support vector regression; (iii) in the context of the Chinese A-share stock market, specific financial indicators such as return on equity, inventory turnover rate, net income growth rate, and debt-to-equity ratio should be given greater consideration compared to other financial metrics.

Empirical Analysis of Portfolio Allocation During Market Turbulence Based on Efficient Frontier

The global financial markets have experienced considerable turmoil due to the COVID-19 pandemic, in this context, portfolio management becomes critically important. This paper employs Monte Carlo Simulation to determine Efficient Frontier of a portfolio comprising fourteen US technology stocks in the period of COVID-19 pandemic by python, which also allocates portfolios for Minimum Volatility and Maximum Sharpe Ratio, along with their key parameters. According to this study, Maximum Sharpe Ratio portfolio outperforms Minimum Volatility portfolio in terms of cumulative return. However, its important to note that Maximum Sharpe Ratio portfolio also experiences a greater maximum drawdown. Additionally, this paper visually depicts the optimal allocation of asset weights across different levels of risk aversion using a chart. Furthermore, it identifies NVDA as the optimal choice for investors who have low degree of risk-aversion due to its high volatility and expected return. Conversely, IBM and CSCO emerge as the preferred choices for risk-averse investors, as they effectively mitigate the portfolios entire risk.

Improving the technology for Inflow Profile Evaluation in horizontal Wells by temperature changes Due to calorimetric Mixing

The paper is devoted to the problem of increasing the effectiveness of temperature logging quantitative interpretation for the inflow profile evaluation in horizontal production wells draining heterogeneous reservoirs with low permeability. Such wells are characterized by an extremely uneven distribution of inflow along the length of the wellbore. One of the ways of quantitative interpretation of temperature logging is based on the effect of calorimetric mixing. It’s widely used to quantify the share of local producing intervals in the total flow rate.The low accuracy of interpretation is associated with the lack of reliable information about the temperature of the fluid flowing into the wellbore. The authors propose an estimate of this parameter based on the similarity of the behavior of the temperature field vs time in the near-wellbore zone of a reservoir during periods of stable production and the periods of the well shut-in. This relationship is confirmed by the results of modeling the temperature field of the “well – reservoir” system, taking into account changes in a wide range of reservoir permeability and thermal properties of the reservoir, the geometry of hydraulic fractures in the reservoir, the flowing fluids, as well as the parameters of the well production targets. The logging technology recommended by the authors involves the registration of several temperature profiles along the length of the wellbore at the beginning of the well production with the maximum rate and drawdown and during the well shut-in. Their integrated analysis based on the behavior of the temperature field features in time identified on the basis of modeling makes it possible to evaluate with a high degree of certainty the dynamics of the temperature of the gas-liquid mixture coming from reservoirs to the wellbore during production periods. This provides the required accuracy in the quantitative assessment of the inflow profile from mixing anomalies.The proposed approaches to the interpretation of thermograms are applicable in the analysis of the results of non-stationary temperature logging results in horizontal and vertical wells during the production from heterogeneous reservoirs both through perforation and multi-stage hydraulic fracturing.

New insights into the glacial and relative sea-level history of the western Fraser Lowland based on sediment cores from geotechnical drilling for the Evergreen Tunnel, British Columbia, Canada

Abstract Geotechnical drilling for a tunnel between Port Moody and Burnaby, BC, Canada, uncovered a buried fjord. Its sedimentary fill has a thickness of at least 130 m and extends more than 37 m below present mean sea level. Recovered sediments record cyclical growth and decay of successive Cordilleran ice sheets. The oldest sediments comprise 58 m of almost stoneless silt conformably overlying ice-proximal sediments and till, which in turn overlie bedrock. These sediments may predate Marine Isotope Stage (MIS) 4. Glacial sediments assigned to MIS 4 overlie this basal succession and, in turn, are overlain by MIS 3 interstadial sediments and sediments from two MIS 2 glacial advances. Indicators of relative sea-level elevations that bracket glacial deposits of MIS 4 and 2 indicate the cyclic existence of moat-like isostatic depressions in the front of expanding ice sheets. Compared with present sea level, these depressions were at least 160 m during the onsets of MIS 4 and MIS 2. Assuming a maximum eustatic drawdown of 120 m during MIS 2, isostatic depression may have exceeded 200 m during retreat of glacial ice from the Evergreen tunnel area. This is consistent with region-specific low mantle viscosity and rapid Cordilleran Ice Sheet buildup and wasting.

Comparative Analysis of SVR and LSTM in Stock Price Forecasting Across Market Cycles

This study investigates the predictive capabilities of Support Vector Regression and Long Short-Term Memory networks on stock price trends across different market conditionsbear, bumpy, and bull markets. With the ongoing evolution of machine learning technologies, their application in financial forecasting has shown substantial potential for capturing complex patterns in vast datasets, which traditional models often fail to process efficiently. This study particularly focuses on the performance of these models in forecasting stock prices from the S&P 500 index, evaluated through the lens of Modern Portfolio Theory (MPT). The models are assessed based on their ability to forecast trends and their implications when applied to constructing investment portfolios, evaluating key financial metrics such as expected returns, standard deviation, Sharpe ratio, and maximum drawdown. The findings indicate that while both SVR and LSTM exhibit competence in trend prediction, especially in bull markets, their predictions diverge from actual market performance when applied to portfolio construction under MPT. This discrepancy underscores the need for further refinement in modeling approaches to enhance accuracy and reliability in real-world investment scenarios. This research contributes to the empirical literature by demonstrating the practical implications of deploying advanced machine learning and deep learning models in dynamic market environments and suggests directions for future enhancements.

Pro Trader RL: Reinforcement learning framework for generating trading knowledge by mimicking the decision-making patterns of professional traders

This study proposes a novel reinforcement learning (RL) framework, professional trader RL (Pro Trader RL), which mimics the decision-making patterns and trading philosophy of professional traders in stock trading. By exploiting the characteristics of RL, the framework aims to learn efficient trading strategies while mimicking the trading philosophy and risk management methods of professional traders. The framework takes into account the complex nature of the stock market and presents an integrated approach to RL, from data pre-processing to buying, selling and stop-loss. Pro Trader RL consists of four main modules. Data Preprocessing, Buy Knowledge RL, Sell Knowledge RL and Stop Loss Rule, each of which plays the role of professional traders knowledge. The results of three experiments show that the framework achieves high returns and Sharpe ratio regardless of market conditions and has stable performance with low maximum drawdown (MDD), which is superior to the state-of-the-art research. The proposed framework provides a novel approach to applying RL to the stock market and is expected to be useful and applicable in real-world trading settings.

Doubly Sparse estimator for high-dimensional covariance matrices

The classical sample covariance estimator lacks desirable properties such as consistency and suffers from eigenvalue spreading in high-dimensional settings. Improved estimators have been proposed that shrink sample eigenvalues but retain the eigenvectors of the sample covariance estimator. In high dimensions, however, sample eigenvectors are generally strongly inconsistent, rendering eigenvalue shrinkage estimators suboptimal. A Doubly Sparse Covariance Estimator (DSCE) is developed that goes beyond mere eigenvalue shrinkage: a covariance matrix is decomposed into a signal part, where sparse eigenvectors are estimated via truncation, and an idiosyncratic part, estimated via thresholding. It is shown that accurate estimation is possible if the leading eigenvectors are sufficiently sparse affecting proportionately less than p of the variables. DSCE fills the gap for empirical applications that fall in-between fully sparse settings and conditionally sparse settings: DSCE takes advantage of conditional sparsity implied by factor models while allowing only a subset of variables to load on factors, which relaxes pervasiveness assumption of traditional factor models. An empirical application to the constituents of the S&P 1500 illustrates that DSCE-based portfolios outperform competing methods in terms of Sharpe ratio, maximum drawdown, and cumulative return for monthly and daily data.

Design Algorithmic Trading Strategies with Expert Advisor Using Linear Weighted Moving Average (LWMA) and Stochastic Oscillator Technical Indicators

Earlier this decade, the financial sector saw a paradigm change, with automated trading (AT) systems gaining popularity as essential tools for traders and investors. This research explores deeply the design and implementation of Expert Advisors (EAs) for automated financial built using a combination of the Linear Weighted Moving Average (LWMA) and Stochastic oscillator technical indicators. The EAs are built using the programming language MetaQuotes Language 4 (MLQ4) at Metatrader 4 (MT4) platform, enabling automated trade execution. It implements a machine learning genetic algorithm, trained on historical data to optimize the parameters of the LWMA and Stochastic trading rules. The core strategy relies on the LWMA to identify the overall market trend direction while the Stochastic oscillator provides additional signals for timing entry and exit points based on momentum. The EAs were coded to generate automated buy and sell signals for algorithmic trading (AT) based on a set of defined rules using thresholds for each indicators. Extensive historical backtesting using Gold (XAU/USD) currency pair across multiple timeframes from 5-minute (M5) up to 4-hour (H4) charts was conducted using 5 years of price data from 2019 to 2023 for evaluation. The goal of this study is to assess if the EAs could potentially produce consistent profits over time while minimizing drawdowns in different market conditions. The results demonstrate that the system was able to generate annual returns ranging from 3.04% up to 232.19% depending on the aggression of the timeframe settings. Meanwhile, maximum drawdowns were controlled to reasonable levels between 0.5% to 8.27% which is below 10% of potential loss throughout the backtests. An hourly timeframe configuration provided a balanced blend between strong profitability and drawdown control based on the backtest analysis. All the timeframes used for the test show positive results and the M5 timeframe is the best chosen timeframe to trade using this EAs implementation.

RISK AND RETURN ANALYSIS OF SIP V/S LUMP SUM INVESTMENT IN MUTUAL FUND SCHEME (EQUITY & HYBRID & ELSS)

This paper conducts a comprehensive risk and return analysis comparing systematic investment plan (SIP) and lump sum investment approaches in various categories of mutual fund schemes, including equity, hybrid, and Equity Linked Savings Schemes (ELSS). The study examines historical data to evaluate the performance, volatility, and risk-adjusted returns of both SIP and lump sum investments over different time horizons. Key metrics such as annualized returns, standard deviation, Sharpe ratio, and maximum drawdown are employed to provide insights into the comparative risk and return profiles of these investment strategies. The findings contribute to a better understanding of the trade-offs between SIP and lump sum investments in different mutual fund categories, aiding investors in making informed decisions based on their risk tolerance, investment objectives, and time horizon

Diversified Reward-Risk Parity in Portfolio Construction

Abstract We introduce diversified risk parity embedded with various reward-risk measures and more generic allocation rules for portfolio construction. We empirically test the proposed reward-risk parity strategies and compare their performance with an equally-weighted risk portfolio in various asset universes. The reward-risk parity strategies we tested exhibit consistent outperformance evidenced by higher average returns, Sharpe ratios, and Calmar ratios. The alternative allocations also reflect less downside risks in Value-at-Risk, conditional Value-at-Risk, and maximum drawdown. In addition to the enhanced performance and reward-risk profile, transaction costs can be reduced by lowering turnover rates. The diversified reward-risk parity allocations gain superior performance in the Carhart four-factor analysis.

The Effect of Sectoral Diversification on Return and Risk in Portfolio Management: An Application in Borsa Istanbul

This paper investigates sectoral diversification within Borsa Istanbul, aiming to elucidate its impact on portfolio risk and return dynamics. Spanning the timeframe from 2020 to 2022, the study meticulously analyzes stocks from pivotal sectors, including banking, energy, and iron and steel. Employing a robust methodology, the research harnesses Monte Carlo simulations to generate many hypothetical portfolios, subsequently evaluating them on the Efficient Frontier to identify optimal risk-return trade-offs. Key performance metrics, such as the Sharpe Ratio, Sortino Ratio, and Maximum Drawdown, further enrich the analysis, providing a granular view of portfolio behaviors. The significance of this study lies in its bridging of theoretical constructs of diversification with the tangible realities of an emerging market like Borsa Istanbul. Our main findings underscore the potential benefits of sectoral diversification while highlighting the complexities inherent in portfolio construction. The insights gleaned offer valuable guidance for investors, emphasizing the delicate balance between risk mitigation and return optimization in a diversified portfolio.

Macroeconomic momentum and cross-sectional equity market indices

Momentum is a well-known and studied artefact of financial markets. In this paper, we investigate whether momentum in a country’s macroeconomic variables is related to the future performance of equities in that country. We find that the past economic trends of a country’s fundamentals are positively associated with the equity market index returns. Based on that, an economic momentum portfolio of buying (selling) equity index in countries with relatively strong (weak) economic past trends exhibits an annualised Sharpe ratio of 0.87. The economic momentum portfolio outperforms benchmarks regarding rewards to variability and maximum drawdown and yields an annualised alpha of 3.72%, leaving 95% of the returns unexplained by the benchmarks.

Enhanced Genetic-Algorithm-Driven Triple Barrier Labeling Method and Machine Learning Approach for Pair Trading Strategy in Cryptocurrency Markets

In the dynamic world of finance, the application of Artificial Intelligence (AI) in pair trading strategies is gaining significant interest among scholars. Current AI research largely concentrates on regression analyses of prices or spreads between paired assets for formulating trading strategies. However, AI models typically exhibit less precision in regression tasks compared to classification tasks, presenting a challenge in refining the accuracy of pair trading strategies. In pursuit of high-performance labels to elevate the precision of classification models, this study advanced the Triple Barrier Labeling Method for enhanced compatibility with pair trading strategies. This refinement enables the creation of diverse label sets, each tailored to distinct barrier configurations. Focusing on achieving maximal profit or minimizing the Maximum Drawdown (MDD), Genetic Algorithms (GAs) were employed for the optimization of these labels. After optimization, the labels were classified into two distinct types: High Risk and High Profit (HRHP) and Low Risk and Low Profit (LRLP). These labels then serve as the foundation for training machine learning models, which are designed to predict future trading activities in the cryptocurrency market. Our approach, employing cryptocurrency price data from 9 November 2017 to 31 August 2022 for training and 1 September 2022 to 1 December 2023 for testing, demonstrates a substantial improvement over traditional pair trading strategies. In particular, models trained with HRHP signals realized a 51.42% surge in profitability, while those trained with LRLP signals significantly mitigated risk, marked by a 73.24% reduction in the MDD. This innovative method marks a significant advancement in cryptocurrency pair trading strategies, offering traders a powerful and refined tool for optimizing their trading decisions.

PORTFOLIO MODELS FOR OPTIMIZING DRAWDOWN DURATION

The drawdown duration, which measures the time elapsed since the portfolio obtained its maximum value, is an important criterion in active portfolio management for institutional investors. Although several optimization models exist for controlling portfolio drawdown magnitude (i.e. the percentage drop in portfolio value from its latest peak value), developing similar models for the drawdown duration has received minimal attention in the literature. Therefore, this paper develops a family of models for optimizing average, maximum and tail drawdown duration formulated as mixed-integer linear programming (MILP) problems, allowing the utilization of powerful solvers to identify optimal asset portfolios. We apply the developed models to real data on historical returns to compare their performance against traditional and drawdown-based portfolio selection models. The results indicate that the developed models lead to decrease in drawdown duration levels both in in-sample and out-of-sample tests. The constructed efficient frontiers also show a clear trade-off between minimizing drawdown duration and maximizing expected returns.