Search results

Cryptocurrency markets are gaining popularity, with over 23,000 cryptocurrencies in 2023 and a total market valuation of 870.81 billion USD in 2023. With its increasing popularity, cryptocurrencies are also susceptible to volatility. Predicting the price with the least fallacy or more accuracy has become the need of the hour as it significantly influences investment decisions.

This study aims to create a dynamic forecasting model using the ensemble method and test the forecasting accuracy of top 15 cryptocurrencies’ prices. Statistical and econometric model prediction accuracy is examined after hyper tuning the parameters. Drawing inferences from the statistical model, an ensemble model using machine learning (ML) algorithms is developed using gradient-boosted regressor (GBR), random forest regressor (RFR), support vector regression (SVR) and multi-layer perceptron (MLP). Validation curves are utilized to optimize model parameters and boost prediction accuracy.

It is found that when the price movement exhibits autocorrelation, the autoregressive integrated moving average (ARIMA) model and the ensemble model performed better. ARIMA, simple linear regression (SLR), random forest (RF), decision tree (DT), gradient boosting (GB) and multi-model regression (MLR) ensemble models performed well with coins, showing that trends, seasonality and historical price patterns are prominent. Furthermore, the MLR approach produces more accurate predictions for coins with higher volatility and irregular price patterns.

Although the dataset includes crisis period data, anomalies or outliers are yet to be explicitly excluded from the analysis. The models employed in this study still demonstrate high accuracy in predicting cryptocurrency prices despite these outliers, suggesting that the models are robust enough to handle unexpected fluctuations or extreme events in the market. However, the lack of specific analysis on the impact of outliers on model performance is a limitation of the study, as it needs to fully explore the resilience of the forecasting models under adverse market conditions.

The present study contributes to the body of literature on ensemble methods in forecasting crypto price in general, potentially influencing future studies on price forecasting. The study motivates the researchers on empirical testing of our framework on various asset classes. As a result, on the prediction ability of ensemble model, the study will significantly influence the decision-making process of traders and investors. The research benefits the traders and investors to effectively develop a model to forecast cryptocurrency price. The findings highlight the potential of ensemble model in predicting high volatile cryptocurrencies and other financial assets. Investors can design the investment strategies and asset allocation decisions by understanding the relationship between market trends and consumer behavior. Investors can enhance portfolio performance and mitigate risk by incorporating these insights into their decision-making processes. Policymakers can use this information to design more effective regulations and policies promoting economic stability and consumer welfare. The study emphasizes the need for using diversified model to understand the market dynamics and improving trading strategies.

This research, to the best of our knowledge, is the first to use the above models to develop an ensemble model on the data for which the outliers have not been adjusted, and the model still outperformed the other statistical, econometric, ML and deep learning (DL) models.

加密貨幣市場越來越受歡迎; 於2023年,不同種類的加密貨幣為數已超過23,000種; 同年,它們的總市場估值為八千七百零八點壹億美元。雖然加密貨幣越來越受歡迎,但它們仍然容易受到波動性的影響。預測謬誤減至最少的價格或作出更準確的價格預測就成為某些特定時刻的首要事項,這是因為投資決策會顯著地受到這些預測的影響。

研究人員擬以集成學習方法來創造一個動態預測模型,並以此模型測試預測15個頂尖加密貨幣價格的準確性。 研究人員調校超參數後,便審查統計及計量經濟學模式的預測準確性。研究人員基於從統計模式作出的推斷,研製一個使用機器學習算法的集成模型。研究人員在研製這個集成模型時,使用了梯度提升迴歸變量、隨機森林迴歸、支持向量迴歸和多層感知器。 驗證曲線被用來優化模型參數,以及提高預測的準確性。

研究人員發現,當價格變動展示自相關時,差分整合移動平均自我迴歸模型和集成模型會表現得更好; 另外,若使用加密貨幣,差分整合移動平均自我迴歸模型、簡單線性迴歸、隨機森林、決策樹、梯度提升和多模型迴歸集成模型會有良好的表現。再者,就波動性較高和價格模式不規則的加密貨幣而言,採用多重線性迴歸的方法會使預測更為準確。

據我們所知,這是首個研究,以上述的各個模型來研發一個集成模型,而這個集成模型,雖建基於異常值並未調整的數據,但它的表現卻比其它的統計、計量經濟學、多重線性和深度學習等的模型更為優良。

This study aims to gauge the effect of rural–urban migration and its challenges on the urban development of Bengaluru. This study examines the driving forces behind urbanization and its impact on social, economic and environment areas. The research helps to establish the sustainable city planning, after evaluation of specific challenges of zones, and this mitigation will optimize government investment and reduce cost.

Bengaluru is used as a study area to examine the interaction of migration and urban development. The study covers the period between 2011 and 2019. Panel data analysis is applied to measure the effect of urban development indicators on urban migration. The authors applied the integrated urban metabolism analysis tool to quantify the urban development indicators and identified the most critical areas for migrants. Later, authors proposed mitigation measures based on alternate scenario approach.

The authors found that there is a mixed effect of urban migration on urban development across various zones in Bengaluru. Besides, the authors suggest how planned collaboration should play a significant role in urban planning and optimize city planning judiciously. Effective mitigation measures should be developed based on zone-specific core issues, and practical trainings, research, public awareness campaigns and skill up-gradation of migrants would enhance the socio-economic and environmental conditions.

The study will support the ongoing and upcoming initiatives launched by the Government of India i.e. Awas Yojna, Atmanirbhar Bharat and Swach Bharat.

The structured city planning suggested in the study will help to save wastage of resources and cost and time of developers and policymakers. This will also help to upgrade the status of migrants and enhance the ambience of city around social, economic and environment fronts.

The first of its kind of innovative model mapped in the study area establishes a link between strategic city planning under rural–urban migration and urban development.

This study aims to explore the perceptions of investors regarding the risks associated with funding renewable energy projects in India, as well as the various factors that influence these perceptions. The investigation is limited to debt providers and seeks to pinpoint the primary risks that bankers perceive and the drivers that shape these perceptions.

This study draws on interviews and surveys of Indian bank executives, investigating how finance providers perceive risks in the Indian context and the factors driving such perceptions. Qualitative interviews have been used for operationalizing “risk perception” within the renewable energy domain, followed by a quantitative survey and exploratory factor analysis.

The authors find that experience and capacity are the most important factors that account for 30% of the overall variance. The second factor, which accounts for 15% of the variance, includes the perceived risks in funding renewable energy projects as compared to infrastructure projects. Among individual risks, the authors find that bankers perceive technological risk to be the lowest (5%) and contractual and regulatory risks as the highest (66%) in renewable energy projects.

The study contextualizes risk perception toward renewable energy investments in the Indian context by drawing from the risk perception literature and qualitative interviews with senior bankers. It presents empirical evidence on the decision-making behavior of bankers, who are important stakeholders of the renewable energy ecosystem. The main limitation of the study is the relatively small sample, and generalizing the results to the broader population might require a larger sample. This will facilitate the use of confirmatory factor analysis and structural equation modeling, which can facilitate a more comprehensive understanding of risk perceptions in renewables financing.

Insights gained can be used to provide policy recommendations for improving the financing ecosystem of renewable energy projects. The research significantly contributes to the extant literature within the renewable energy financing domain for emerging economies.

This study gauges the profitability and performance of Indian commercial banks under the technology advancements. In this study, the authors identified three domains that give advantage to banks due to technology incorporation, that is, increased sales revenue, reduced operating expenses, and increased employee productivity. The authors assess the effect of these domains on banks’ profitability and performance. This study is conducted for the period between the years 2003 and 2018 across 34 public and private banks for empirical analysis. The authors examined the impact of investment in technology on the profitability using panel data analysis and evaluated the long-term effect of technology investment using the vector error correction model. This study found that there is a mixed effect of technology spend on the profitability and performance of Indian banks, where private sector banks are more aggressive in technology investment as compared to the public sector banks. This study recommends an optimal technology-related strategy to gain improved productivity for the banking business, that is, planned technology reserves, customer awareness campaigns about technology-enabled products, and robust employee–customer motivation policy.

This study aims to identify and gauge the sustainability indicators (SUSIs) for sustainable Hydroelectric Power (HEP) project development. It examines major SUSIs under the social, economic and environmental (SEE) fronts and categorizes them under push and pull impacts which helps to identify challenges and opportunities associated with projects. Additionally, the study calculates an empirical sustainability index (SI) to assess the sustainability level of HEP. Finally, the study suggests mitigation measures across stakeholders, which will optimize government/developer/investor investments.

This paper examines the interaction of sustainable HEP development with SUSIs using Uttarakhand as a study area. Additionally, SI has been developed quantitatively. For the indicator classification, the authors conducted a literature review and secondary survey of all affected parties, including investors, developers, NGOs and villagers. The fuzzy logic theory (FLT) is used to determine the SI of the study area and classify projects in their level of sustainability. On the basis of expert opinion and literature review, mitigation measures are proposed across stakeholders.

The authors found that there is a mixed effect of SUSIs on HEP development across various projects in Uttarakhand. Furthermore, the authors suggest that index-based assessment and planned collaboration play a significant role in sustainable HEP development. Mitigation measures should be suggested to all affected stakeholders based on specific project issues, i.e. collaborations, training, public awareness campaigns, and initiatives by the government that would improve sustainability conditions.

In addition to supporting the ongoing and upcoming initiatives launched by the Government of India, including the Green Energy Corridor, independent power producers (IPPs); and the India-Renewable Resources Development Project with IDA and participates in Net zero target.

The structured, sustainable HEP planning suggested in the study will help to conserve society, economy, save resources and in parallel reduce the cost and time of developers and policymakers. This will also help to improve the socioeconomic status of the villagers and prolong the life of the project.

The innovative SI-based push-pull approach identifies a sustainable HEP project planning.

This paper aims to focus on the different types of insider-led cyber frauds that gained mainstream attention in recent large-scale fraud events involving prominent Indian banking institutions. In addition to identifying and classifying cyber fraud, the study maps them on a severity scale for optimal mitigation planning.

The methodology used for identification and classification is an analysis of a detailed literature review, a focus group discussion with risk and vigilance officers and cyber cell experts, as well as secondary data of cyber fraud losses. Through machine learning-based random forest, the authors predicted the future of insider-led cyber frauds in the Indian banking business and prioritized and predicted the same. The projected future reveals the dominance of a few specific cyber frauds, which will make it easier to develop a fraud mitigation model based on a victim-centric approach.

The paper concludes with a conceptual framework that can be used to ensure a sustainable cyber fraud mitigation ecosystem within the scope of the study. By using the findings of this research, policymakers and fraud investigators will be able to create a more robust environment for banks through timely detection of cyber fraud and prevent it appropriately before it happens.

The study focuses on fraud, risk and mitigation from a victim-centric perspective and does not address it from the fraudster’s perspective. Data availability was a challenge. Banks are recommended to compile data that can be used for analysis both by themselves and other policymakers.

The structured, sustainable cyber fraud mitigation suggested in the study will provide an agile, quick, proactive, stakeholder-specific plan that helps to safeguard banks, employees, regulatory authorities, customers and the economy. It saves resources, cost and time for bank authorities and policymakers. The mitigation measures will also help improve the reputational status of the Indian banking business and prolong the banks’ sustenance.

The innovative cyber fraud mitigation approach contributes to the sustainability of a bank’s ecosystem quickly, proactively and effectively.

In the past few years, HB-like protocols have gained much attention in the field of lightweight authentication protocols due to their efficient functioning and large potential applications in low-cost radio frequency identification tags, which are on the other side spreading so fast. However, most published HB protocols are vulnerable to man-in-the-middle attacks such as GRS or OOV attacks. The purpose of this research is to investigate security issues pertaining to HB-like protocols with an aim of improving their security and efficiency.

In this paper, a new and secure variant of HB family protocols named HB-MP* is proposed and designed, using the techniques of random rotation. The security of the proposed protocol is proven using formal proofs. Also, a prototype of the protocol is implemented to check its applicability, test the security in implementation and to compare its performance with the most related protocol.

The HB-MP* protocol is found secure against passive and active adversaries and is implementable within the tight resource constraints of today’s EPC-type RFID tags. Accordingly, the HB-MP* protocol provides higher security than previous HB-like protocols without sacrificing performance.

This paper proposes a new HB variant called HB-MP* that tries to be immune against the pre-mentioned attacks and at the same time keeping the simple structure. It will use only lightweight operations to randomize the rotation of the secret.