Search Results (59)

In recent years, computational intelligence techniques have significantly contributed to the automation and optimization of trading strategies. Despite the increasing sophistication of predictive models, classical technical indicators such as dual Simple Moving Averages (2-SMA) remain popular due to their simplicity and interpretability. This work proposes an adaptive trading system that combines the 2-SMA strategy with a learning-based metaheuristic optimizer known as the Learning-Based Linear Balancer ($L{B}^2$). The objective is to dynamically adjust the strategy’s parameters to maximize returns in the highly volatile cryptocurrency market. The proposed system is evaluated through simulations using historical data of the BTCUSDT futures contract from the Binance platform, incorporating real-world trading constraints such as transaction fees. The optimization process is validated over 34 training/test splits using overlapping 60-day windows. Results show that the $L{B}^2$-optimized strategy achieves an average return on investment (ROI) of 7.9% in unseen test periods, with a maximum ROI of 17.2% in the best case. Statistical analysis using the Wilcoxon Signed-Rank Test confirms that our approach significantly outperforms classical benchmarks, including Buy and Hold, Random Walk, and non-optimized 2-SMA. This study demonstrates that hybrid strategies combining classical indicators with adaptive optimization can achieve robust and consistent returns, making them a viable alternative to more complex predictive models in crypto-based financial environments. Full article

Predicting short-term buy and sell signals in financial markets remains a significant challenge for algorithmic trading. This difficulty stems from the data’s inherent volatility and noise, which often leads to spurious signals and poor trading performance. This paper presents a novel algorithmic trading model for silver that combines fine-tuned Convolutional Neural Networks (CNNs) with a decision filter based on the Relative Strength Index (RSI). The technique allows for the prediction of buy and sell points by turning time series data into chart images. Daily silver price per ounce data were turned into chart images using technical analysis indicators. Four pre-trained CNNs, namely AlexNet, VGG16, GoogLeNet, and ResNet-50, were fine-tuned using the generated image dataset to find the best architecture based on classification and financial performance. The models were evaluated using walk-forward validation with an expanding window. This validation method made the tests more realistic and the performance evaluation more robust under different market conditions. Fine-tuned VGG16 with the RSI filter had the best cost-adjusted profitability, with a cumulative return of 115.03% over five years. This was nearly double the 61.62% return of a buy-and-hold strategy. This outperformance is especially impressive because the evaluation period was mostly upward, which makes it harder to beat passive benchmarks. Adding the RSI filter also helped models make more disciplined decisions. This reduced transactions with low confidence. In general, the results show that pre-trained CNNs fine-tuned on visual representations, when supplemented with domain-specific heuristics, can provide strong and cost-effective solutions for algorithmic trading, even when realistic cost assumptions are used. Full article

This paper explores the optimization of the bullwhip effect (BWE) and inventory costs considering price information symmetry in an omnichannel environment, offering novel insights into managing supply chain dynamics. We examine the pick-up lead time in the “buy online and pick up in store” (BOPS) channel as a critical operational factor, analyzing how the interaction with the ordering lead time affects omnichannel supply chain performance. The research highlights the impacts of the BOPS strategy on demand and inventory information, developing a comparative examination of the BWE and inventory expenses within various supply chain contexts. We discover that the interplay between ordering lead time and pick-up lead time significantly affects both inventory costs and the BWE of omnichannel retailers, with these impacts presenting an inverse relationship. While numerous studies have validated that product returns can restrain the information distortion in supply chains, our findings reveal that this relationship holds true in omnichannel retail only within specific supply chain contexts. This comprehensive approach offers valuable insights for omnichannel supply chain managers seeking to optimize the BOPS strategy and improve overall operational efficiency. Full article

This paper proposes a comprehensive deep-learning framework, SentiStack, for Bitcoin price forecasting and trading strategy evaluation by integrating multimodal data sources, including market indicators, macroeconomic variables, and sentiment information extracted from financial news and social media. The model architecture is based on a Stacking-LSTM ensemble, which captures complex temporal dependencies and non-linear patterns in high-dimensional financial time series. To enhance predictive power, sentiment embeddings derived from full-text analysis using the DeepSeek language model are fused with traditional numerical features through early and late data fusion techniques. Empirical results demonstrate that the proposed model significantly outperforms baseline strategies, including Buy & Hold and Random Trading, in cumulative return and risk-adjusted performances. Feature ablation experiments further reveal the critical role of sentiment and macroeconomic inputs in improving forecasting accuracy. The sentiment-enhanced model also exhibits strong performance in identifying high-return market movements, suggesting its practical value for data-driven investment decision-making. Overall, this study highlights the importance of incorporating soft information, such as investor sentiment, alongside traditional quantitative features in financial forecasting models. Full article

Cryptocurrency markets are characterized by high volatility, nonlinear dependencies, and limited transparency, making short-term forecasting particularly challenging for both researchers and practitioners. To address these complexities, this study introduces a Temporal Fusion Transformer (TFT)-based forecasting framework that integrates on-chain and technical indicators to improve predictive performance and inform tactical trading decisions. By combining multi-source features—such as Spent Output Profit Ratio (SOPR), Total Value Locked (TVL), active addresses (AA), exchange net flow (ENF), Realized Cap HODL Waves, and the Crypto Fear and Greed Index—with classical signals like Relative Strength Index (RSI) and moving average convergence divergence (MACD), the model captures behavioral patterns, investor sentiment, and price dynamics in a unified structure. Five major cryptocurrencies—BTC, ETH, USDT, XRP, and BNB—serve as the empirical basis for evaluation. The proposed TFT model is benchmarked against LSTM, GRU, SVR, and XGBoost using standard regression metrics to assess forecasting accuracy. Beyond prediction, a signal-based trading strategy is developed by translating model outputs into daily buy, hold, or sell signals, with performance assessed through a comprehensive set of financial metrics. The results suggest that integrating attention-based deep learning with domain-informed indicators provides an effective and interpretable approach for multi-asset cryptocurrency forecasting and real-time portfolio strategy optimization. Full article

This study examines whether portfolio optimization can be effectively based on annual changes in the harmonized index of consumer prices (HICP) data. Specifically, we assess whether asset allocation based on consumer expenditure can generate superior returns compared to static or equal-weighted asset allocation. To explore this, we use consumer expenditure data from HICP statistics categorized by COICOP. Our findings indicate that this strategy outperforms a buy-and-hold benchmark by 13.32% in terms of the Sharpe Ratio and exceeds an annual equal-weighted rebalancing strategy by 3.11%. Additionally, both the Calmar and Sterling Ratios demonstrate improved performance, further reinforcing the robustness of this approach. Furthermore, a hypothetical scenario where sector weights from the end of the given year—though not yet available during the year—are used suggests even greater improvements in performance. A high-sample bootstrap simulation confirms that the observed performance differences are not random but reflect the independent effectiveness of asset allocation based on consumer expenditure trends. This result strengthens the validity of our backtesting findings, indicating that the examined strategy could generate excess returns compared to passive portfolio managment and fixed-weight rebalancing approaches. The result of the study is therefore the development of an effective portfolio rebalancing strategy. Full article

This study aims to explore how key opinion leader (KOL) characteristics influence users’ purchase intentions in live shopping. Using a mixed-methods approach, the study combines real-time pop-up text mining and questionnaires, analyzed via Latent Dirichlet Allocation (LDA) topic modeling and a research framework integrating the stimulus–organism–response (SOR) model with pleasure–arousal–dominance (PAD) theory. Results indicate that KOL characteristics—namely professionalism, popularity, attractiveness, and entertainment—enhance users’ pleasure, arousal, and trust. These emotions boost impulse buying intentions but not planned ones. Planned purchase intention acts as a partial mediator, whereas impulse purchase intention serves as a full mediator. This research uncovers the intricate mechanism linking KOL traits to user emotions and purchase intentions. By integrating PAD theory and the SOR model, it examines emotional mediators, addresses prior theoretical gaps, offers vital insights for refining live-streaming marketing strategies, and holds substantial theoretical and practical significance for the sustainable growth of live-streaming e-commerce. Full article

Because of the theoretical challenges posed by the Efficient Market Hypothesis with respect to technical analysis, the effectiveness of technical indicators in high-frequency trading remains inadequately explored, particularly at the minute-level frequency, where the effects of the microstructure of the market dominate. This study evaluates the integration of traditional technical indicators with Random Forest regression models using minute-level SPY data, analyzing 13 distinct model configurations. Our empirical results reveal a stark contrast between in-sample and out-of-sample performance, with $R^2$ values deteriorating from 0.749–0.812 during training to negative values in testing. A feature importance analysis demonstrates that primary price-based features dominate the predictions made by the model, accounting for over 60% of the importance, while established technical indicators, such as RSI and Bollinger Bands, account for only 14–15%. Although the indicator-enhanced models achieved superior risk-adjusted metrics, with Rachev ratios between 0.919 and 0.961, they consistently underperformed a simple buy-and-hold strategy, generating returns ranging from −2.4% to −3.9%. These findings challenge conventional assumptions about the usefulness of technical indicators in algorithmic trading, suggesting that in high-frequency contexts, they may be more relevant to risk management rather than to predicting returns. For practitioners and researchers, our findings indicate that successful high-frequency trading strategies should focus on adaptive feature selection and regime-specific modeling rather than relying on traditional technical indicators, as well as indicating the critical importance of robust out-of-sample testing in the development of a model. Full article

This paper presents a stock trading recommendation system that integrates news sentiment analysis with the relative strength index (RSI) to provide informed buy–sell decisions. The system uses a rule-based natural language processing (NLP) approach to analyze recent news articles and combines the resulting sentiment scores with the RSI, which tracks stock momentum. By evaluating seven days of news data, the system assigns a sentiment score (1 to 100) that reflects market sentiment, while the RSI identifies overbought or oversold conditions. This combined approach allows traders to make data-driven buy, sell, or hold decisions in real time. In this study, we conducted a comparative study with benchmark indices across various subsets of stocks to evaluate their relative performance, highlighting our system’s competitive edge in terms of accuracy, profitability, and lightweight design with low computational cost. The results showed the system’s adaptability across different market segments and its potential to enhance trading outcomes. By integrating real-time sentiment analysis with technical indicators, the system offers a practical and actionable investment strategy. Full article

In this study, we introduce a detailed framework for predicting market conditions and selecting stocks by integrating machine learning techniques with ontological financial analysis. The process starts with ontology-based stock selection, categorizing companies using fundamental financial indicators such as liquidity, profitability, debt ratios, and growth metrics. For instance, firms showcasing favorable debt-to-equity ratios along with robust revenue growth are identified as high-performing entities. This classification facilitates targeted analyses of market dynamics. To predict market states—categorizing them into bull, bear, or neutral phases—the framework utilizes a Non-Stationary Markov Chain (NMC), BERT, to assess sentiment in financial news articles and Long Short-Term Memory (LSTM) networks to identify temporal patterns. Key inputs like the Sentiment Index (SI) and Illiquidity Index (ILLIQ) play essential roles in dynamically influencing regime predictions within the NMC model; these inputs are supplemented by variables including GARCH volatility and VIX to enhance predictive precision further still. Empirical findings demonstrate that our approach achieves an impressive 97.20% accuracy rate for classifying market states, significantly surpassing traditional methods like Naive Bayes, Logistic Regression, KNN, Decision Tree, ANN, Random Forest, and XGBoost. The state-predicted strategy leverages this framework to dynamically adjust portfolio positions based on projected market conditions. It prioritizes growth-oriented assets during bull markets, defensive assets in bear markets, and maintains balanced portfolios in neutral states. Comparative testing showed that this approach achieved an average cumulative return of 13.67%, outperforming the Buy and Hold method’s return of 8.62%. Specifically, for the S&P 500 index, returns were recorded at 6.36% compared with just a 1.08% gain from Buy and Hold strategies alone. These results underscore the robustness of our framework and its potential advantages for improving decision-making within quantitative trading environments as well as asset selection processes. Full article

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. Full article

In this work, we explore the application of deep reinforcement learning (DRL) to algorithmic trading. While algorithmic trading is focused on using computer algorithms to automate a predefined trading strategy, in this work, we train a Double Deep Q-Network (DDQN) agent to learn its own optimal trading policy, with the goal of maximising returns whilst managing risk. In this study, we extended our approach by augmenting the Markov Decision Process (MDP) states with sentiment analysis of financial statements, through which the agent achieved up to a 70% increase in the cumulative reward over the testing period and an increase in the Calmar ratio from 0.9 to 1.3. The experimental results also showed that the DDQN agent’s trading strategy was able to consistently outperform the benchmark set by the buy-and-hold strategy. Additionally, we further investigated the impact of the length of the window of past market data that the agent considers when deciding on the best trading action to take. The results of this study have validated DRL’s ability to find effective solutions and its importance in studying the behaviour of agents in markets. This work serves to provide future researchers with a foundation to develop more advanced and adaptive DRL-based trading systems. Full article

Devising a financial trading strategy that allows for long-term gains is a very common problem in finance. This paper aims to formulate a mathematically rigorous framework for the problem and compare and contrast the results obtained. The main approach considered is based on Dynamic Bayesian Networks (DBNs). Within the DBN setting, a long-term as well as a short-term trading strategy are considered and applied on twelve equities obtained from developed and developing markets. It is concluded that both the long-term and the medium-term strategies proposed in this paper outperform the benchmark buy-and-hold (B&H) trading strategy. Despite the clear advantages of the former trading strategies, the limitations of this model are discussed along with possible improvements. Full article

The COVID-19 pandemic disrupted global food waste patterns through unanticipated shifts in composition and quantities. This review explores the impacts of COVID-19 on food waste generation and management approaches in the Near East and North Africa (NENA) region during the recovery phase. This paper comprehensively explores food loss and waste in the NENA region. It presents a detailed analysis of pandemic-induced changes in household food waste behaviors, analyses the integration of circular economy principles in recovery strategies and policy implications, and outlines potential avenues for future research in this critical area. The key findings are threefold: First, this study reaffirms that food waste is a critical challenge in NENA, contributing to food insecurity, water scarcity, and environmental issues. Second, the pandemic catalyzed a dichotomy in consumer behaviors—panic buying initially increased waste, while hardship measures later encouraged sustainable waste reduction practices like meal planning and leftover use. Third, adopting a circular economy approach holds potential, yet its implementation remains limited in terms of curbing food waste and promoting sustainability in NENA. Overall, while the pandemic accentuated the urgency of tackling food waste, it also stimulated innovative policy thinking and strategic planning for building more resilient food systems. This paper concludes that leveraging pandemic-driven sustainability mindsets while addressing systemic drivers of waste will be key to mitigating food waste and its impacts moving forward. This paper offers timely insights into the evolving food waste management landscape in NENA, underscoring the need for integrated policies to navigate post-pandemic recovery effectively. Full article

In this study, we delve into the financial market to compare the performance of prominent AI and robotics-related stocks against traditional IT indices, such as the Nasdaq, and specialized AI and robotics ETFs. We evaluate the role of these stocks in diversifying portfolios, analyzing their return potential and risk profiles. Our analysis includes various investment scenarios, focusing on common AI-related stocks in the United States. We explore the influence of risk management strategies, ranging from “buy and hold” to daily rebalancing, on AI stock portfolios. This involves investigating long-term strategies like buy and hold, as well as short-term approaches, such as daily rebalancing. Our findings, covering the period from 30 April 2021, to 15 September 2023, show that AI-related stocks have not only outperformed in recent years but also highlight the growing “AI bubble” and the increasing significance of AI in investment decisions. The study reveals that these stocks have delivered superior performance, as indicated by metrics like Sharpe and Treynor ratios, providing insights into market trends and financial returns in the technology and robotics sectors. The results are particularly relevant for investors and traders in the AI sector, offering a balanced view of potential returns against the risks in this rapidly evolving market. This paper adds to the financial market literature by demonstrating that investing in emerging trends, such as AI, can be more advantageous in the short term compared to traditional markets like the Nasdaq. Full article