ETF Price Research Articles

APPLYING OF RANDOM FOREST AND SUPPORT VECTOR MACHINE IN PREDICTING PRICES OF URANIUM COMPANIES

Due to the war in Ukraine and restrictions on the export of hydrocarbons from Russia by the European countries, uranium companies are again becoming an interesting sector in terms of investment. Consequently, it is important for investors to have accurate forecasts of uranium sector. This article applies machine learning algorithms such as the Random Forests and the Support Vector Machine to predict future URA ETF prices for the next five periods. The study was conducted using data on the ETF Global X Uranium for the period from 08/11/2010 to 31/05/2023 was obtained from investing.com. The data contains information about the stock such as High, Low, Open, Close, Adjacent close and Volume and several well-known technical indicators. The research showed that both the Random Forest and the Support Vector Machine forecast prices with less bias than the classic ARIMA model. The Random Forest algorithm forecasted prices with a constant level of bias over the forecasting period, while the error of the forecasts calculated by the Support Vector Machine algorithm for the first three periods was the lowest compared to the rest of the analyzed models. Research showed that the Random Forest algorithm and the Support Vector Machine can be used to make correct predictions for uranium sector.

ETF 가격 방향성 예측을 위한 그래프 구조 학습 기반 신경망

ETF 가격 방향성 예측을 위한 그래프 구조 학습 기반 신경망

Döviz Kurunun BYF’ler Üzerindeki Etkileri: BİST’ten Kanıtlar

This study better investigates the possible relationship between exchange rates and ETF prices in the BIST to understand ETF investors' behaviour in the Turkish economy. Conventional and Fourier-based co-integration and causality analysis methods were employed to test models. According to findings, although the exchange rate has no direct effect on ETF prices in Türkiye, it is effective on ETF prices indirectly via the risk and share of foreign investors. The originality of the study lies in models built with additional control variables. In doing so, we measure the direct and indirect effects of the exchange rate on the Turkish economy.

Is there a nexus between NFT, DeFi and carbon allowances during extreme events?

PurposeThe authors target the interrelationships between non-fungible tokens (NFTs), decentralized finance (DeFi) and carbon allowances (CA) markets during 2021–2023. The recent shift of crypto and DeFi miners from China (the People's Republic of China, PRC) green hydro energy to dirty fuel energies elsewhere induces investments in carbon offsetting instruments; this is a backdrop to the authors’ investigation.Design/methodology/approachThe quantile vector autoregression (VAR) approach is employed to examine extreme-quantile-connectedness and spillovers among the NFT Index (NFTI), DeFi Pulse Index (DPI), KraneShares Global Carbon Strategy ETF price (KRBN) and the Solactive Carbon Emission Allowances Rolling Futures Total Return Index (SOLCARBT).FindingsAt bull markets, DPI is the only consistent net shock transmitter as NFTI transmits innovations only at the most extreme quantile. At bear markets, KRBN and SOLCARBT are net shock transmitters, while NFTI is the only consistent net shock receiver. The receiver-transmitter roles change as a function of the market conditions. The increases in the relative tail dependence correspond to the stress events, which make systemic connectedness augment, turning market-specific idiosyncratic considerations less relevant.Originality/valueThe shift of digital asset miners from the PRC has resulted in excessive fuel energy consumption and aggravated environmental consequences regarding NFTs and DeFi mining. Although there exist numerous studies dedicated to CA trading and its role in carbon print reduction, the direct nexus between NFT, DeFi and CA has never been addressed in the literature. The originality of the authors’ research consists in bridging this void. Results are valuable for portfolio managers in bull and bear markets, as the authors show that connectedness is more intense under such conditions.

When passive funds affect prices: evidence from volatility and commodity ETFs

Abstract This article studies exchange-traded funds’ (ETFs) price impact in the most ETF-dominated asset classes: volatility (VIX) and commodities. I propose a new way to measure ETF-related price distortions based on the specifics of futures contracts. This allows me to isolate a component in VIX futures prices that is strongly related to the rebalancing of ETFs. I derive a novel decomposition of ETF trading demand into leverage rebalancing, calendar rebalancing, and flow rebalancing, and show that trading against ETFs is risky. Leverage rebalancing has the largest effects on the ETF-related price component. This rebalancing amplifies price changes and exposes ETF counterparties to variance.

Predicting ETF prices using linear regression

Machine learning has allowed computers to analyze data and make future predictions based on those dates. One of the most common and easiest to implement machine learning algorithms used to do this is simple linear regression. Simple linear regression finds trends in a data set by graphing a line that shows the relationship between two variables. This paper will show how Simple linear regression can predict future ETF prices by finding linear trends in two particular exchange-traded funds: Invesco QQQ and vanguard VGT, predict their value six months later using their five-year closing price in yahoo finance and compare their respective predicted growth rate.

Economic and Financial Determinants of Gold ETF Price Volatility on the U.S. Futures Market (COMEX)

Economic and Financial Determinants of Gold ETF Price Volatility on the U.S. Futures Market (COMEX)

Bubble in Carbon Credits during COVID-19: Financial Instability or Positive Impact (“Minsky” or “Social”)?

Incentivizing businesses to lower carbon emissions and trade back excess carbon allowances paved the way for rapid growth in carbon credit ETFs. The use of carbon allowances as a hedging alternative fueled this rally further, causing a shift to speculation and forming repetitive bubbles. Speculative bubbles are born from euphoria, yet, they are relatively predictable, provided their pattern matches the log periodic power law (LPPL) with specific stylized facts. A “Minsky moment” identifies a clear speculative bubble as a signal of financial system instability, while a “Social bubble” is regarded as relatively positive, increasing in the long run, infrastructure spending and development. The aim of this paper is to investigate whether various carbon credit bubbles during the pandemic period caused financial instability or had a positive impact (“Minsky” or “Social”). Particularly, we investigate the carbon credit bubble behavior in the ETF prices of KRBN, GRN (Global Carbon Credit tracking ETFs), and the SOLCARBT index during the COVID-19 pandemic period by adopting the log-periodic power law model (LPPL) methodology, which has been widely used, over the past decade, for detecting bubbles and crashes in various markets. In conclusion, these bubbles are social and propelled by the newfound interest in carbon credit trading, for obvious reasons.

Does the Diversity and Solvency of Authorized Participants Matter for Bond ETF Arbitrage? Evidence from the Dash for Cash Episode

Authorized participants’ (APs) arbitrage in primary markets for ETF shares plays a key role in limiting dislocation in ETF prices. This paper builds a novel dataset of detailed US bond ETF-AP relationships and shows that high AP leverage played a significant role in weakening this arbitrage during the dash-for-cash episode of March 2020. The strength of the arbitrage relationship linking price signals to primary market activity weakened by 77 percent in ETFs related to more leveraged APs versus 64 percent for ETFs linked to less leveraged APs. This effect was particularly strong among those ETFs focusing on less liquid asset classes, relying on APs engaging in high-frequency trading strategies, and unrelated to banks and bank holding companies. Policy announcements by the Federal Reserve did not have had a strong impact in restoring arbitrage strength. AP leverage constraints operated in parallel to constraints faced by lead-market makers in secondary ETF markets, which were more closely related to regulatory capital limits.

Tracking Error and Portfolio of Futures ETFs According to Futures Contracts Maturity

Purpose - The purpose of this research is to confirm the tracking error of futures ETFs according to their portfolio weights with the most recent and next month’s maturity futures contracts. Design/Methodology/Approach - This research used futures indexes, futures contracts, ETF prices, and net asset value data of ETFs from the Fn Data Guide. Tracking error of futures ETFs, volatility, spread rate, and weight error variables were calculated from the data, and panel regression models from Hausman (1978) were used for empirical analysis. Findings - This research has two findings. First, the tracking error from D-3 (criterion: most recent maturity of futures contracts) to D-day (criterion: most recent maturity of futures contracts) was higher than the other trading days’ tracking errors. This is because the futures index is calculated with the most recent and next month’s maturity futures contracts, and the weight is different. Second, if the weight error between the most recent month’s maturity and next month’s maturity futures contracts is high in ETF portfolios, the tracking error is high. Research Implications - The results from the empirical analysis are as follows. When portfolio managers in futures ETFs do not adjust the futures contract weights between the most recent month’s maturity and next month’s maturity exactly, the tracking error is high. Therefore, managers should reflect the weight of the portfolio exactly.

Time-Varying Wavelet-Based Applications for Evaluating the Water-Energy Nexus

This paper quantifies the rising global dynamic, interconnected relationship between energy and water commodities. Over the last decade, increased international concern has emerged about the water-energy nexus. However, recent research still lacks a quantified understanding of the role of water within a financial-economic view of the nexus. The complexity of commodity markets contributes to this lack of understanding. These markets consist of a wide variety of participants having different objectives, resulting in non-stationary time series. Wavelets are mathematical functions that detect common time-localized oscillations in non-stationary time series. The novelty of our analysis lies in applying wavelet techniques to better quantify the financial implications and understand opportunities of the dynamic relationship that exists in the water-energy nexus. Using daily water and energy commodity ETF price data from 2007 to 2017 we deconstruct each of the time series into different horizon components and evaluate their respective wavelet transforms. Comparing the wavelet squared coherence (WSC) and the windowed scalogram difference (WSD) allows us to specify nexus similarities and differences. We further analyze the wavelet local multiple correlations (WLMC) by including S&P500 ETF price data to conditionally eliminate market effects. Previous studies heavily focused on the qualitative relationships between water and energy. Whereas the analysis in this paper, to the best of our knowledge, is the first to confirm the time-varying relationship in a quantitative manner. The most significant financial-economic result from our analysis is that water prices, at certain time horizons, lead energy prices during specific localized economic events.

Impacts of the Fed Corporate Credit Facilities through the Lenses of ETFs and CDX

In this study, we use the liquid and efficient bond ETF prices and CDX spreads to quantify the effects of the announcements of the Primary and Secondary Market Corporate Credit Facilities on the underlying corporate bonds. We find that those announcements triggered: (i) large and positive jumps in the prices of directly-eligible ETFs as well as ETFs holding eligible bonds and their close substitutes; (ii) a discrete drop in the perceived credit risk of eligible bonds especially following the April 9th announcement; (iii) a roaring back of investment-grade issuance and a pick-up in high-yield issuance. Importantly, across all ETFs in our sample, the magnitude of their price response does not seem directly related to the size of the reduction in either credit risk or liquidity risk, but rather appears to reflect mostly the eligibility of the ETF and its underlying bonds at the Federal Reserve facilities. This leads us to believe that the main factor driving the reaction to the announcements might be the elimination of “disaster risk” for eligible issuers.

Levered ETFs

Regular and levered ETFs are markedly different financial innovations. Regular ETFs improve liquidity: they are more liquid than their underlying stocks. In contrast, although the levered ETF market has a substantially higher turnover, it also has a significantly higher bid-ask spreads and larger price impacts. Our interpretation is that levered ETFs are appealing to short-term levered speculators. The aggregate cost levered ETF investors incur is around 10% of the market capitalization, or around $2 billion, each year. Moreover, regular ETF investors appear to be momentum traders, while levered ETF investors are contrarians: For regular (levered) ETFs, their monthly fund flows are strongly positively (negatively) correlated with past returns. Finally, arbitrage forces push ETF prices partially towards their NAVs, and this mechanism is less effective for levered ETFs than for regular ones.

Volatility spillovers for spot, futures, and ETF prices in agriculture and energy

The agricultural and energy industries are closely related, both biologically and financially. The paper discusses the relationship and the interactions on price and volatility, and on the covolatility spillover effects for these two industries. The interaction and covolatility spillovers, or the delayed effect of a returns shock in one asset on the subsequent volatility or covolatility in another asset, between the energy and agricultural industries is the primary emphasis of the paper. Although there has already been significant research on biofuel and biofuel-related crops, only a few published papers have been concerned with volatility spillovers. It must be emphasized that there have been numerous technical errors in the theoretical and empirical research, which need to be addressed. The paper considers futures prices as a widely-used hedging instrument, and also considers an interesting new hedging instrument, ETF, which is regarded as index futures when investors manage their portfolios. In the empirical analysis, multivariate conditional volatility diagonal BEKK models are estimated for comparing patterns of covolatility spillovers. The paper provides a new way of analyzing and describing the patterns of covolatility spillovers, which should be useful for the future empirical analysis of estimating and testing covolatility spillover effects.

Research on Quantitative Investment Strategies Based on Deep Learning

This paper takes 50 ETF options in the options market with high transaction complexity as the research goal. The Random Forest (RF) model, the Long Short-Term Memory network (LSTM) model, and the Support Vector Regression (SVR) model are used to predict 50 ETF price. Firstly, the original quantitative investment strategy is taken as the research object, and the 15 min trading frequency, which is more in line with the actual trading situation, is used, and then the Delta hedging concept of the options is introduced to control the risk of the quantitative investment strategy, to achieve the 15 min hedging strategy. Secondly, the final transaction price, buy price, highest price, lowest price, volume, historical volatility, and the implied volatility of the time segment marked with 50 ETF are the seven key factors affecting the price of 50 ETF. Then, two different types of LSTM-SVR models, LSTM-SVR I and LSTM-SVR II, are used to predict the final transaction price of the 50 ETF in the next time segment. In LSTM-SVR I model, the output of LSTM and seven key factors are combined as the input of SVR model. In LSTM-SVR II model, the hidden state vectors of LSTM and seven key factors are combined as the inputs of the SVR model. The results of the two LSTM-SVR models are compared with each other, and the better one is applied to the trading strategy. Finally, the benefit of the deep learning-based quantitative investment strategy, the resilience, and the maximum drawdown are used as indicators to judge the pros and cons of the research results. The accuracy and deviations of the LSTM-SVR prediction models are compared with those of the LSTM model and those of the RF model. The experimental results show that the quantitative investment strategy based on deep learning has higher returns than the traditional quantitative investment strategy, the yield curve is more stable, and the anti-fall performance is better.

Does the Lending Rate Impact ETF's Prices?

In this paper we developed an econometric model to empirically test the hard-to-borrow model of Avellaneda and Lipkin (2009) where asset prices jump as result of ``buy-in" procedures. The model is estimated using an extent version of simulated maximum likelihood (SML) for a selected group of Leveraged ETF, mainly short LETFs, because these instruments have been sporadically hard-to-borrow and are liquids. In general we do not find enough statistical evidence supporting that hard-to-borrow effect impacts LETFs prices. On the other hand, we did find statistical evidence supporting the jump-diffusion model for some Leveraged ETFs.

ETF Arbitrage and International Correlation

We show that investment decisions of country ETF market participants measured by ETF market order imbalances are driven by global shocks, rather than local risks. We demonstrate that the ETF arbitrage mechanism is one of the key channels through which global shocks propagate to local economies leading to increased return correlation with the U.S. market, limiting the benefits from international diversification. Staggered introduction of country ETFs increases the return correlations between underlying foreign and U.S. market indices. We find that countries with stronger ETF price discovery and lower limits to arbitrage have a higher comovement with the U.S. market lending further support for the proposed arbitrage mechanism.

Trading on ETF mispricings

PurposePrior literature has shown deviations between ETF prices and their net-asset-value (NAV) to exist. Fulkerson and Jordan (2013, p. 31) question “if there exists a true tradeable strategy” to exploit these inefficiencies. The purpose of this paper is to implement a profitable daily long-short trading strategy based on price/NAV information and explicitly accounting for trading costs.Design/methodology/approachFor a sample of European sector ETFs, the authors analyze gross and net returns of a long-short trading strategy in the capital asset pricing model and Fama-French three-factor model.FindingsThe authors document positive gross excess return for the long-short trading strategy in all sample periods, but net excess returns to be positive only between 2008 and 2010.Research limitations/implicationsThe results document a profitable long-short trading strategy exploiting deviations between ETF prices and NAV and highlight the impact of trading costs in ETF markets. Due to the limited availability of historic trading cost data, the research uses a comparatively small sample size.Practical implicationsThe net profitability of long-short trading in ETFs is only found in times of high uncertainty in the stock market.Originality/valueThe inclusion of trading costs enables a detailed comparison between gross and net returns in ETF trading, addressing potential limits to arbitrage.

Paper profits or real money? Trading costs and stock market anomalies in country ETFs

Are the quantitative equity strategies for country selection robust to implementation costs? To answer this question, we conduct a comprehensive examination of the country-level strategies so far. We review, classify, and replicate 120 equity anomalies within a sample of 42 country equity indices for the years 1996–2017. Next, using ETF price and spread data, we test the effect of real-life conditions and trading costs on the anomaly performance. We also examine three cost-mitigation strategies: infrequent rebalancing, capitalization-based weighting, and focus on low-cost securities. We find that 46% of the long-only monthly rebalanced anomaly portfolios display significant alphas, concentrated strongly among strategies based on value, momentum, and liquidity. The effect of transaction costs proves largely lethal to returns, leaving only a handful of anomalies profitable. Less frequent rebalancing (annually) helps to regain the effectiveness of the strategies, increasing the monthly alphas on the long-only anomaly portfolios to 0.44% on average.

Time-Varying Wavelet-Based Applications for Evaluating the Water-Energy Nexus

This paper quantifies the rising global dynamic, interconnected relationship between energy and water commodities. Over the last decade, increased international concern has emerged about the water-energy nexus. However, recent research still lacks a quantified understanding of the role of water within a financial-economic view of the nexus. The complexity of commodity markets contributes to this lack of understanding. These markets consist of a wide variety of participants having different objectives, resulting in non-stationary time series. Wavelets are mathematical functions that detect common time-localized oscillations in non-stationary time series. The novelty of our analysis lies in applying wavelet techniques to better understand the financial implications and opportunities of the dynamic relationship that exists in the water-energy nexus. Using daily water and energy commodity ETF price data from 2007 to 2017 we deconstruct each of the time series into different horizon components and evaluate their respective wavelet transforms. Comparing the wavelet squared coherence (WSC) and the windowed scalogram difference (WSD) allows us to specify nexus similarities and differences. We further analyze the wavelet local multiple correlations (WLMC) by including S&P500 ETF price data. The most significant financial-economic result from our analysis is that water prices, at certain time horizons, lead energy prices during specific localized economic events.