Direction Of Price Changes Research Articles

Fuzzy Clustering Algorithm for Trend Prediction of The Digital Currency Market

Digital currencies, such as Bitcoin (BTC), Litecoin (LTC), Ethereum (ETH), Stellar (XLM) and Tether (USDT), have been attracting the interest of investors and speculators. Over the last several years, the exponential growth in the value of digital currency has captured the interest of many individuals who see it as an attractive investment opportunity. After all, investors must deal with the expected volatility of Bitcoin prices as part of their investments. The future development of cryptocurrency can be challenging to forecast because of the extreme unpredictability and disorder of external events. In this research, fuzzy models for cryptocurrency price forecasting using a level set-based Fuzzy Clustering Based on Multi-Criteria Decision-Making (FC-MCDM). Compared to linguistic and functional fuzzy clustering, the construction and processing of fuzzy rules in a multi-criteria decision-making-based collection set differ. Based on level sets, the model produces the weighted average of the functions that active fuzzy rules provide as output. In the model's outputs, the activation levels of the fuzzy rules are represented directly by the output functions. Computational experiments are carried out to test the efficacy of the level-set approach for one-step-ahead prediction of cryptocurrency closing prices. Meanwhile, level set-based fuzzy clustering outperforms the other methods when the direction of price change evaluates performance

A critical comparison between the gross substitutes and complements conditions

In a transferable utility matching environment, the gross substitutes condition (Kelso and Crawford 1982) and the gross complements condition (Rostek and Yodar 2020) guarantee the existence of equilibrium outcomes. We show that the difference between the two conditions is pinpointed to the direction of price changes: the former condition requires that any set of demanded contracts is still demanded after the prices of other contracts increase, while the latter condition requires that any set of demanded contracts is still demanded after the prices of other contracts decrease.

Forecasting cryptocurrencies prices using data driven level set fuzzy models

The paper develops fuzzy models to forecast cryptocurrencies prices using a data-driven fuzzy modeling procedure based on level set. Data-driven level set is a novel fuzzy modeling method that differs from linguistic and functional fuzzy modeling in how the fuzzy rules are built and processed. The level set-based model outputs the weighted average of output functions of active fuzzy rules. Output functions map the activation levels of the fuzzy rules directly in model outputs. Computational experiments are done to evaluate the level set method in one-step-ahead forecasting of the closing prices of cryptocurrencies. Comparisons are made with the autoregressive integrated moving average, multi layer neural network, and the naïve random walk as a benchmark for Cardano, Binance Coin, Bitcoin, Ethereum, Chainlink, Litecoin, Tron, Stellar, Monero and Ripple. The results suggest that the random walk outperforms most methods addressed in this paper, confirming the Meese–Rogoff puzzle for the case of digital coins, i.e. the difficulty to surpass the naïve random walk in predicting exchange rates. However, when performance is measured by the direction of price change, the level set-based fuzzy modeling performs best amongst the remaining methods.

Asymmetric own- and cross-price effects: the case of US outbound tourism demand

ABSTRACT Past studies have generally assumed that tourism demand is perfectly price-reversible, and tourists respond to price increases and decreases symmetrically. This paper aims to investigate the potential asymmetric effects of tourism prices on outbound US tourism demand for Canada, Mexico, the UK, France, and Italy. Using the linear and nonlinear autoregressive distributed lag (ARDL) approach, the results show that in the long run, asymmetric responses to own-price changes are found for Canada, the UK, France, and Italy. Regarding own-price elasticities, US tourists tend to respond strongly to price increases, while they are insensitive to price decreases in the long run. These findings differ from the results from the linear model in which the own-price elasticities tend to be insignificant. In the short run, tourism demand appears to be more responsive to price decreases than to price increases, suggesting that tourists’ behaviour differs between the short and long run. Examination of the cross-price elasticities indicates that the degrees of substitutability and complementarity between destinations vary, depending on the direction of price changes.

Forecasting significant stock price changes using neural networks

Stock price prediction is a rich research topic that has attracted interest from various areas of science. The recent success of machine learning in speech and image recognition has prompted researchers to apply these methods to asset price prediction. The majority of literature has been devoted to predicting either the actual asset price or the direction of price movement. In this paper, we study a hitherto little explored question of predicting significant changes in stock price based on previous changes using machine learning algorithms. We are particularly interested in the performance of neural network classifiers in the given context. To this end, we construct and test three neural network models including multi-layer perceptron, convolutional net, and long short term memory net. As benchmark models we use random forest and relative strength index methods. The models are tested using 10-year daily stock price data of four major US public companies. Test results show that predicting significant changes in stock price can be accomplished with a high degree of accuracy. In particular, we obtain substantially better results than similar studies that forecast the direction of price change.

COMPARATIVE ANALYSIS OF QUALITY TO FORECAST MODELS OF EXCHANGE TRADED FUNDS DYNAMICS

The article is devoted to the comparative analysis to forecast models of exchange-traded investment funds dynamics. The exchange traded investment fund was chosen for the study as a modern investment instrument, which managed to combine the best features of stocks and mutual investment funds. However, despite the advantages of this financial instrument, the main task of the investor is the ability to predict its dynamics. To date, there are many forecast models, but the ability to create a reliable and accurate forecast remains extremely important.Two exchange traded funds were selected for forecasting: SPDR S&P 500 ETF TRUST (the stock ticker is SPY) and VanEck Vectors Gold Miners (the stock ticker is GDX). Based on daily prices for the period from January 2016 to January 2020, forecast models of two types were built: linear and nonlinear. Namely, linear models of moving average and exponential smoothing (Holt model) were selected. The neural network model was chosen as a nonlinear model. It turned out that the quality assessment of all models is quite high. However, the constructed forecasts showed that despite the high quality of the obtained statistical models of moving average and exponential smoothing, forecasting with their help is possible only for the forecast horizon, which is one trading day. The neural network model, conversely, shows a worse forecast for the first forecast value, but captures the dynamics and direction of price changes in both the exchange-traded investment fund SPY and GDX. That is, with the help of training, the neural network is able to establish hidden nonlinear patterns of price dynamics. But the horizon of the neural network forecast is also limited: in research it is established that the forecast on the basis of a neural network model it is expedient to build no more than for one exchange week.

Simulating Vertical Mergers and the Vertical GUPPI Approach

Moresi and Salop (2013) have extended the “upward pricing pressure” approach used in analyzing horizontal mergers to the analysis of vertical mergers. They present test expressions called the vGUPPIu and vGUPPId to see if the upstream and downstream prices will rise as a result of the merger. This approach has gained acceptance. In this paper we present the results of Monte Carlo simulations of a vertical merger for a simple setup with one upstream monopolist and two downstream firms. In the simulations, the upstream price paid by the remaining downstream rival can either rise or fall. The downstream price always falls. The downstream rival may exit even when the upstream price falls. Based on these simulations, we see if the Moresi and Salop formulas predict the directions of price changes correctly. We also derive a variation on the Moresi and Salop formulation, arriving at different vGUPPI formulas. Overall, neither approach does well. Both versions of the vGUPPIu predict upstream price increases, whereas the simulations show many decreases. The merged firm’s downstream price always falls in the simulations. The Moresi and Salop downstream price test is correct 82.1% of the time, whereas the variant is correct 100% of the time.

Estimation of level-I hidden liquidity using the dynamics of limit order-book

Many invisible forms of market liquidity exist since many market participants often prefer to hide their trade intentions. Among others, hidden limit order placements are allowed in many public exchanges and generate hidden liquidity. As a result, only part of market liquidity is visible, leading to markets with incomplete information. This study investigates how hidden liquidity alters the econophysical dynamics of limit order books and price impact functions. Accordingly, this study proposes an estimation method of level-I hidden liquidity (hidden waiting orders at best prices) using only publicly available data. Though direct validation with actual hidden liquidity was not possible, this study demonstrates that estimated hidden liquidity provides two empirical benefits. First, estimated hidden liquidity enhances an existing price-impact function and achieves an R-squared value of 70.8% on average. Second, estimated hidden liquidity improves order-book pressure models that forecast the future direction of price change. Using the central notion of market liquidity, this study investigates the different subjects of high-frequency data in an integrated manner, such as the dynamics of execution, price-impact function, and order-book pressure.

Simulating Vertical Mergers and the Vertical GUPPI Approach

Moresi and Salop (2013) have extended the “upward pricing pressure” approach used in analyzing horizontal mergers to the analysis of vertical mergers. They present test expressions called the vGUPPIu and vGUPPId to see if the upstream and downstream prices will rise as a result of the merger. This approach has gained acceptance. In this paper we present the results of Monte Carlo simulations of a vertical merger for a simple setup with one upstream monopolist and two downstream firms. In the simulations, the upstream price paid by the remaining downstream rival can either rise or fall. The downstream price always falls. The downstream rival may exit even when the upstream price falls. Based on these simulations, we see if the Moresi and Salop formulas predict the directions of price changes correctly. We also derive a variation on the Moresi and Salop formulation, arriving at different vGUPPI formulas. Overall, neither approach does well. Both versions of the vGUPPIu predict upstream price increases, whereas the simulations show many decreases. The merged firm’s downstream price always falls in the simulations. The Moresi and Salop downstream price test is correct 82.1% of the time, whereas the variant is correct 100% of the time.

Development of an Ensemble Learning-based intelligent model for Stock Market Forecasting

The use of artificial intelligence-based models have shown that the market is predictable despite its uncertainty and unstable nature. The most important challenge of the proposed models in the stock market is the accuracy of the results and increasing the forecasting efficiency. Another challenge, which is a prerequisite for making decision and using the results of the forecast for profitability of transactions, is to forecast the trend of stock price movements in forecasting price. To overcome the mentioned challenges, this paper employs ensemble learning (EL) model using intelligence-based learners and metaheuristic optimization methods to maximize the improvement of forecasting performance. In addition, in order to consider the direction of price change in stock price forecasting, a two-stage structure is used. In the first stage, the next movement of the stock price (increase or decrease) is forecasted and its outcome is then employed to forecast the price in the second stage. In both stages, genetic algorithm (GA) and particle swarm optimization (PSO) technique are used to optimize the aggregation results of the base learners. The evaluation results of stock market dataset show that the proposed model has higher accuracy compared to other models used in the literature.

Developing the Criterion of Exchange Quotation Prediction Quality for Metal Trader Decision Support

The main purpose of this article is to present a criterion for assessing the quality of forecasting nickel exchange prices to support the decision-making of a metal trader, taking into account the specifics of their commercial activities. We consider the commercial operation of a metal trading company, which consists in purchasing a metal with a view to its resale in 14 days. Most of these operations occur in nickel-rich alloys, which suggests that their prices are largely determined by nickel quotes on the LME (London Metal Exchange). Therefore, metal traders need forecasting models with a long lead time series with a high degree of volatility. One of the first assumptions suggests that in order to ensure profitable trading, it is necessary, first of all, to correctly predict the direction of price change. On the other hand, it is intuitively clear that the better the model, the more likely it will be to guess the further trend. However, it remains an open question as to what accuracy of the forecast will provide the so-called break-even point to the metal trader. This work is devoted to the search for this facet. Another assumption that the quality of any model depends on the degree of volatility of the predicted time series helps to find the exact point from which we can talk about the possibility of successful trading. Taking into account these provisions, a criterion has been developed for assessing the quality of forecasting models, which makes it possible to state with high probability that the use of a forecast that meets it will ensure commercial success for the metal trader. It is also important to note that the quality of the model can be judged only after comparing its accuracy with the characteristics of the considered time series. The prediction error itself does not give an exhaustive picture of the quality of the applied model.

Modeling and forecasting multifractal wavelet scale: Western market versus eastern market

This leading primary study is about modeling multifractal wavelet scale time series data using multiple wavelet coherence (MWC), continuous wavelet transform (CWT) and multifractal detrended fluctuation analysis (MFDFA) and forecasting with vector autoregressive fractionally integrated moving average (VARFIMA) model. The data is acquired from Yahoo Finances!, which is composed of 1671 daily stock market of eastern (NIKKEI, TAIEX, KOPSI) and western (SP500, FTSE, DAX) markets. Once the co-movement dependencies on time-frequency space are determined with MWC, the coherent data is extracted out of raw data at a certain scale by using CWT. The multifractal behavior of the extracted series is verified by MFDFA and its local Hurst exponents have been calculated obtaining root mean square of residuals at each scale. This inter-calculated fluctuation function time series has been re-scaled and used to estimate the process with VARFIMA model and forecasted accordingly. The results have shown that the direction of price change is determined without difficulty and the efficiency of forecasting has been substantially increased using highly correlated multifractal wavelet scale time series data.

On empirical likelihood test for predictability

Predicting asset prices is a critical issue in statistics and finance. In this article, by incorporating the recent advances in nonparametric approaches, we propose the empirical likelihood test for the predictability for the direction of price changes. Under some regularity conditions, the test statistic has an asymptotic χ2 distribution under the null hypothesis that the direction of price change cannot be predicted. This test procedure is easy to implement and presents better finite sample performances than other popular causality tests, as reported in some Monte Carlo experiments.HightlightsWe propose a non parametric likelihood test for predictability.The test involves no user-chosen parameter or estimation of covariance matrix.The test is simple to implement and has standard asymptotics.The test has significantly better sizes than several popular tests with satisfactory power.

Cascading Logistic Regression Onto Gradient Boosted Decision Trees to Predict Stock Market Changes Using Technical Analysis

In the data mining and machine learning fields, forecasting the direction of price change can be generally formulated as a supervised classfii cation. This paper attempts to predict the direction of daily changes of the Nasdaq Composite Index (NCI) and of the Standard & Poor's 500 Composite Stock Price Index (S&P 500) covering the period from January 3, 2012 to December 23, 2016, and of the Shanghai Stock Exchange Composite Index (SSEC) from January 4, 2010 to December 31, 2014. Due to the complexity of stock index data, we carefully combine raw price data and eleven technical indicators with a cascaded learning technique to improve the performance of the classifi cation. The proposed learning architecture LR2GBDT is obtained by cascading the logistic regression (LR) model onto the gradient boosted decision trees (GBDT) model. Given the same test conditions, the experimental results show that the LR2GBDT model performs better than the baseline LR and GBDT models for these stock indices, according to the performance metrics Hit ratio, Precision, Recall and F-measure. Furthermore, we use these models to develop simple trading strategies and assess their performance in terms of their Average Annual Return, Maximum Drawdown, Sharpe Ratio and Average Annualized Return/Maximum Drawdown. When transaction costs and buy-sell thresholds are taken into account, the best trading strategy derived from LR2GBDT model still reaches the highest Sharpe Ratio and clearly beats the buy-and-hold strategy. The performances are found to be both statistically and economically signi ficant.

Gain and loss of money in a choice experiment. The impact of financial loss aversion and risk preferences on willingness to pay to avoid renewable energy externalities

We examine how the direction of price changes affects the value people place on avoiding renewable energy externalities in Poland. Additionally, we investigate the influence of individuals' financial loss aversion and financial risk preferences on this valuation. In our study we conduct a choice experiment survey in which respondents' choices indicate the value they place on avoiding wind, solar, and biomass externalities. We combine this survey with a financial lottery choice task that elicits the respondents' risk preferences and degree of loss aversion. In the choice experiment we use both increases and decreases in electricity bills to depict the uncertain effect of new sources of energy generation on the current price level. This design allows us to investigate if obtained values are independent of the payment mechanism. In the analyzed context, our results indicate that marginal utility of money seems to be lower with a rebate on the energy bill than with a surcharge. We find that financial risk preferences affect people's choices both in a case of a surcharge and a rebate, while loss aversion for money affects them just in the case of a rebate. Loss aversion for money seems to not be present during a buying process. The results indicate that the more risk seeking people are in a financial domain the more they are willing to pay for proposed changes in renewable energy development, at the same time people who are more risk averse require less compensation before they accept externalities from renewable electricity production. Moreover, a higher compensation is required by people who are more loss averse with regard to money.

The prospective impact of food pricing on improving dietary consumption: A systematic review and meta-analysis.

BackgroundWhile food pricing is a promising strategy to improve diet, the prospective impact of food pricing on diet has not been systematically quantified.ObjectiveTo quantify the prospective effect of changes in food prices on dietary consumption.DesignWe systematically searched online databases for interventional or prospective observational studies of price change and diet; we also searched for studies evaluating adiposity as a secondary outcome. Studies were excluded if price data were collected before 1990. Data were extracted independently and in duplicate. Findings were pooled using DerSimonian-Laird's random effects model. Pre-specified sources of heterogeneity were analyzed using meta-regression; and potential for publication bias, by funnel plots, Begg's and Egger's tests.ResultsFrom 3,163 identified abstracts, 23 interventional studies and 7 prospective cohorts with 37 intervention arms met inclusion criteria. In pooled analyses, a 10% decrease in price (i.e., subsidy) increased consumption of healthful foods by 12% (95%CI = 10–15%; N = 22 studies/intervention arms) whereas a 10% increase price (i.e. tax) decreased consumption of unhealthful foods by 6% (95%CI = 4–8%; N = 15). By food group, subsidies increased intake of fruits and vegetables by 14% (95%CI = 11–17%; N = 9); and other healthful foods, by 16% (95%CI = 10–23%; N = 10); without significant effects on more healthful beverages (-3%; 95%CI = -16-11%; N = 3). Each 10% price increase reduced sugar-sweetened beverage intake by 7% (95%CI = 3–10%; N = 5); fast foods, by 3% (95%CI = 1–5%; N = 3); and other unhealthful foods, by 9% (95%CI = 6–12%; N = 3). Changes in price of fruits and vegetables reduced body mass index (-0.04 kg/m2 per 10% price decrease, 95%CI = -0.08–0 kg/m2; N = 4); price changes for sugar-sweetened beverages or fast foods did not significantly alter body mass index, based on 4 studies. Meta-regression identified direction of price change (tax vs. subsidy), number of intervention components, intervention duration, and study quality score as significant sources of heterogeneity (P-heterogeneity<0.05 each). Evidence for publication bias was not observed.ConclusionsThese prospective results, largely from interventional studies, support efficacy of subsidies to increase consumption of healthful foods; and taxation to reduce intake of unhealthful beverages and foods. Use of subsidies and combined multicomponent interventions appear most effective.

A nonparametric approach to test for predictability

Predictability of macroeconomic and financial variables is an important issue in economics. In this paper, we propose a nonparametric test for the predictability of the direction of price changes. The Monte Carlo simulation results show that our method displays better finite-sample property than the traditional parametric Granger causality test (Granger, 1969) and two nonparametric causality tests of Hiemstra and Jones (1994) and Diks and Panchenko (2006).

Market design and the stability of general equilibrium

We employ laboratory methods to study the stability of competitive equilibrium in Scarf's economy (Scarf, 1960). Tatonnement theory predicts that prices are globally unstable for this economy, i.e. unless prices start at the competitive equilibrium they oscillate without converging. Anderson et al. (2004) report that in laboratory double auction markets, prices in the Scarf economy do indeed oscillate with no clear sign of convergence. We replicate their experiments and confirm that tatonnement theory predicts the direction of price changes remarkably well. Prices are globally unstable with adverse effects for the economy's efficiency and the equitable distribution of the gains from trade.We also introduce a novel market mechanism where participants submit demand schedules and prices are computed using Smale's global Newtonian dynamic (Smale, 1976b). If the submitted schedules are competitive – sets of quantities that maximize utility taking prices as given – the resulting outcome is the unique competitive equilibrium of Scarf's economy. In experiments using the schedule market, prices converge quickly to the competitive equilibrium. Besides stabilizing prices, the schedule market is more efficient and results in highly egalitarian outcomes.

The Martingale Restriction and Relative Market Efficiency between KOSPI 200 Index and Index Options Market

This paper examines the martingale restriction for the KOSPI 200 index options market. And in cases of the rejections, we investigate the relative market efficiency between stock index and stock index options market, using approximate entropy (ApEn) method proposed by Pincus (1994), which quantifies a complexity, irregularity and unpredictability in time series. The empirical results of this study clearly reject the martingale restriction and regression analyses indicate that the historical returns of underlying index can explain about 25% of the price differences between option-implied and market index prices but the total trading volume can explain only a small portion of the price differences. These results have cast doubt on the informational efficiency of this market. Comparing the relative market efficiency based on ApEn have showed that the complexity or irregularity of KOSPI 200 index is larger than the index options during the entire sample period. But, Examining separately ApEn of the magnitude and the sign time series which compose log-returns document that stock index options market reflect more efficiently the information about the direction of price changes than the stock index market in 2014 and the efficiency of the index options market about the directional information may be affected by directional traders who prefer certain strategies designed by exploiting past stock market movements.

On possible origins of trends in financial market price changes

We investigate possible origins of the trends in financial markets, where trend we refer to as is a relatively long-term fluctuation observed in price change (price movement), using a simple deterministic threshold model that contains no external driving force term to generate trends forcibly. We find that the trend can be generated by this simple model without any external driving force. Furthermore, from thorough numerical simulations, we obtain two following results: (i) a trend of monotonic increase or decrease can be generated only by dealers’ minuscule price updates for the next deal trying to follow an expected forthcoming direction of price change, (ii) non-monotonic trends spontaneously emerge when dealers cannot obtain accurate information about the number of dealers participating in the next deal. We conclude from these results that the emergence of trends is not necessarily generated by an external driving force but by a natural outcome of the accumulation of minuscule price updates of individual dealers with insufficient information about the next deal.