Prediction Of Future Prices Research Articles

Crude oil price forecasting using K-means clustering and LSTM model enhanced by dense-sparse-dense strategy

Crude oil is an essential energy source that affects international trade, transportation, and manufacturing, highlighting its importance to the economy. Its future price prediction affects consumer prices and the energy markets, and it shapes the development of sustainable energy. It is essential for financial planning, economic stability, and investment decisions. However, reaching a reliable future prediction is an open issue because of its high volatility. Furthermore, many state-of-the-art methods utilize signal decomposition techniques, which can lead to increased prediction time. In this paper, a model called K-means-dense-sparse-dense long short-term memory (K-means-DSD-LSTM) is proposed, which has three main training phrases for crude oil price forecasting. In the first phase, the DSD-LSTM model is trained. Afterwards, the training part of the data is clustered using the K-means algorithm. Finally, a copy of the trained DSD-LSTM model is fine-tuned for each obtained cluster. It helps the models predict that cluster better while they are generalizing the whole dataset quite well, which diminishes overfitting. The proposed model is evaluated on two famous crude oil benchmarks: West Texas Intermediate (WTI) and Brent. Empirical evaluations demonstrated the superiority of the DSD-LSTM model over the K-means-LSTM model. Furthermore, the K-means-DSD-LSTM model exhibited even stronger performance. Notably, the proposed method yielded promising results across diverse datasets, achieving competitive performance in comparison to existing methods, even without employing signal decomposition techniques.

A Stock Index Futures Price Prediction Approach Based on the MULTI-GARCH-LSTM Mixed Model

As a type of financial derivative, the price fluctuation of futures is influenced by a multitude of factors, including macroeconomic conditions, policy changes, and market sentiment. The interaction of these factors makes the future trend become complex and difficult to predict. However, for investors, the ability to accurately predict the future trend of stock index futures price is directly related to the correctness of investment decisions and investment returns. Therefore, predicting the stock index futures market remains a leading and critical issue in the field of finance. To improve the accuracy of predicting stock index futures price, this paper introduces an innovative forecasting method by combining the strengths of Long Short-Term Memory (LSTM) networks and various Generalized Autoregressive Conditional Heteroskedasticity (GARCH)-family models namely, MULTI-GARCH-LSTM. This integrated approach is specifically designed to tackle the challenges posed by the nonstationary and nonlinear characteristics of stock index futures price series. This synergy not only enhances the model’s ability to capture a wide range of market behaviors but also significantly improves the precision of future price predictions, catering to the intricate nature of financial time series data. Initially, we extract insights into the volatility characteristics, such as the aggregation of volatility in futures closing prices, by formulating a model from the GARCH family. Subsequently, the LSTM model decodes the complex nonlinear relationships inherent in the futures price series and incorporates assimilated volatility characteristics to predict future prices. The efficacy of this model is validated by applying it to an authentic dataset of gold futures. The empirical findings demonstrate that the performance of our proposed MULTI-GARCH-LSTM hybrid model consistently surpasses that of the individual models, thereby confirming the model’s effectiveness and superior predictive capability.

Web Trade Analytics

This research introduces an innovative web application developed using the MERN (MongoDB, Express.js, React, Node.js) stack, enhanced with fundamental machine learning algorithms, designed to address the complexities of stock market analysis. The central focus is on creating a user-customizable dashboard, allowing investors to select specific stocks for real-time analysis, sentiment tracking, and future price prediction. The methodology integrates historical stock data with sentiment analysis sourced from news and social media. The machine learning algorithms leverage this data to generate buy or sell recommendations and forecast future price trends. Our findings underscore the practicality of this approach, enhancing investors' abilities to navigate the unpredictable stock market landscape and make informed decisions with an eye on the future. Keywords— Stock Market, MERN Stack, Predictive Analysis, Future Forecasting

Interpretable corn future price forecasting with multivariate time series

AbstractEfforts in corn future price forecasting and early warning play a vital role in guiding the high‐quality development of the agricultural economy. However, recent years have witnessed significant fluctuations in global corn future prices due to the impact of COVID‐19 and the escalating risks associated with geopolitical conflicts. Therefore, there is an urgent need for accurate and efficient methods to forecast corn future prices. To address this challenge, a novel and comprehensive framework for explainable corn future price forecasting is designed. This framework takes into account multiple factors contributing to corn price volatility, including supply and demand dynamics, policy adjustments, international market shocks, global geopolitical risks, and investor concerns within the corn market. During the data processing stage, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is utilized to thoroughly explore the volatility characteristics of historical corn future prices. Additionally, a convolutional neural network (CNN) is employed to extract essential forecasting information from corn news data. To enhance interpretability, a novel JADE–TFT interpretable corn future price prediction model is proposed. This model combines adaptive differential evolution with optional external archiving (JADE) to intelligently and efficiently optimize the parameters of the temporal fusion transformers (TFTs). Furthermore, in the empirical study, the introduction of a global geopolitical risk coefficient, Baidu indices such as “corn” and “corn price,” and quantized corn news text features is shown to improve the accuracy of corn future price predictions. The proposed corn future price prediction framework contributes to the healthy development of the global grain futures market, thereby fostering the growth and well‐being of enterprises involved in the grain industry.

Dynamic Pricing Based on Demand Response Using Actor–Critic Agent Reinforcement Learning

Eco-friendly technologies for sustainable energy development require the efficient utilization of energy resources. Real-time pricing (RTP), also known as dynamic pricing, offers advantages over other pricing systems by enabling demand response (DR) actions. However, existing methods for determining and controlling DR have limitations in managing an increasing demand and predicting future pricing. This paper presents a novel approach to address the limitations of existing methods for determining and controlling demand response (DR) in the context of dynamic pricing systems for sustainable energy development. By leveraging actor–critic agent reinforcement learning (RL) techniques, a dynamic pricing DR model is proposed for efficient energy management. The model’s learning framework was trained using DR and real-time pricing data extracted from the Australian Energy Market Operator (AEMO) spanning a period of 17 years. The efficacy of the RL-based dynamic pricing approach was evaluated through two predicting cases: actual-predicted demand and actual-predicted price. Initially, long short-term memory (LSTM) models were employed to predict price and demand, and the results were subsequently enhanced using the deep RL model. Remarkably, the proposed approach achieved an impressive accuracy of 99% for every 30 min future price prediction. The results demonstrated the efficiency of the proposed RL-based model in accurately predicting both demand and price for effective energy management.

A novel adjusted learning algorithm for online portfolio selection using peak price tracking approach

Online Portfolio Selection (OLPS) has attracted extensive interest in recent years. Accurate prediction of future prices and determining the optimal portfolio selection strategy based on the estimated return is a challenging topic in machine learning. We propose a novel adjusted learning algorithm based on peak price tracking for OLPS to tackle this challenge. The algorithm is based on an aggressive strategy with residual information and transaction costs. We first propose an adjusted online portfolio selection algorithm using Peak Price Tracking Approach (PPTA) to improve the accuracy of return prediction by introducing λ to adjust the impact of peak price and residual term on the predicted price. We then build the Net Profit Maximization (NPM) model with transaction costs. Finally, we integrate the PPTA and the NPM algorithms into a new algorithm called the PPTA-NPM to maximize the cumulative return. Extensive benchmark data experiment results and statistical analysis show that the PPTA algorithm significantly improves the accuracy in predicting the future price, and the integrated PPTA-NPM algorithm is superior to multiple classic OLPS algorithms.

Time Series Analysis and Forecasting of Household Products’ Prices (A Case Study of Nyeri County)

Inflation has a significant impact on both consumable and non-consumable products and plays a critical role in determining the cost of living. The study aimed to investigate the trend of household consumable and non-consumable prices over the past three years and identify the best ARIMA model for future price predictions. The results showed that consumable goods played a greater role in determining the national inflation compared to non-consumable goods. A relationship was found between the changes in local-level prices and national monthly inflation rates, with consumable goods being fitted to an ARIMA (1,2,2) model and national inflation rates to ARIMA (3,1,0). Non-consumable goods were found to be a white noise. The models were found to be adequate in forecasting changes in prices, with their validity confirmed by the Box-Ljung test and autocorrelation coefficients of model residuals. This study demonstrated the importance of analyzing changes in products’ prices at a local level and how it affects the national inflation rate. In future, similar studies can be carried out in different counties and with a more comprehensive model to investigate the impact of the COVID-19 pandemic on the prices of household consumable and non-consumable goods at the local level.

A composite trend representation-based tracking system with historical portfolio data for portfolio optimization

In this paper, we propose a novel tracking system based on composite trend representation and historical portfolio data (CTRHP) for portfolio optimization (PO). In the part of obtaining prediction of price, we introduce the important data of historical portfolio, which is rarely utilized before, to improve the accuracy of measuring investment performance. In addition, we propose a set of correlation coefficient-based similarity measurement functions (CSMFs) to automatically assign different weights to different trend representations, which enables each trend representation to have an impact on future price predictions and set the strength according to their investment performance. In the part of portfolio optimization, a new optimization objective based on generalized increasing factors is proposed to optimize the investment portfolio, and a fast solution algorithm is presented. Extensive experiments on six standard datasets from real financial markets across different assets and different time horizons show that our CTRHP achieves significantly better performance compared with previous state-of-the-art PO systems in investing returns and risk control. Moreover, it has the advantages of being able to tolerate certain transaction fees and running fast, which shows that it is suitable for real financial environments.

Comparison of Future Price Prediction in Context of Machine Learning Approach

Contemporarily, futures markets have become prosper on account of its intrinsic risk hedging function as well as double-side trading advantages compared to Chinese stock market. In this case, finding the suitable and appropriate way to predict future price changes will be a crucial thing for investors and traders of commodity. In context of theoretical analysis in terms of summary of previous models, this article firstly selects features and market information of all trading days from 2016 to 2021 as input. The research sample is the CSI300 stock index futures, and 1-daylow-frequency data is selected. Three price prediction models were built in terms of the data, i.e., linear regression, random forest, and support vector machine algorithms. Accordingly, the random forest algorithm has the lowest error, high accuracy and stability in the prediction of stock index futures price. These results shed light on guiding further exploration of future price prediction based on specific machine learning approach.

Price Prediction of Cude oil, Gold, and Cotton Based on OLS, Random Forest, and Lightgbm

Contemporarily, the predicted price becomes a necessary step for investors in order to gain extra returns. This study applies three regression models (i.e., OLS, Random Forest, and Lightgbm) to forecast the future prices of three products (i.e., crude oil, gold, and cotton) The 0.3 rates is used to split the train and test set. Comparing each graph of errors, two obvious lines representing the original data and predicted data tell the direct result of the advantages and disadvantages of the three models. In the experiment, it is found that the Random Forest model takes part in an important role to predict these three prices. The Random Forest model has less error between the three metrics and displays a closer graph between the original data and predicted data. According to the results, Random Forest model predicts the futures prices accurately and other models can also play the same role for specific futures to some extent. These results shed light on guiding further exploration of future price prediction.

A study on the comparison of technical indicators used in stock price prediction with the BAHP method

Savers want to direct their savings to investment areas where they can get maximum efficiency. This is the most basic feature that a rational investor should have. Stock investors also want to manage their investments with this thought. In this respect, investors conduct detailed research on the sector and stock they plan to invest in. Predictions regarding the possible price formation of the stock in the future is one of these studies. In the finance literature, there are many indicators, ratios, analyzes, indicators and oscillators developed for the future price prediction of the stock. In this study, technical indicators used by licensed professional stock investors were obtained by taking expert opinion. These indicators were conveyed to the experts again to get their opinions with the help of the fuzzy comparison matrix and the experts were asked to compare the variables. The data obtained were analyzed with the Fuzzy Analytical Hierarchy Process (FAHP) method and the technical indicators and ratios used by the experts were listed according to a certain hierarchy. As a result of the analysis, it has been determined that the most important ratio in the stock price estimation process is the MV/BV ratio. While EBIT is the second most important ratio in stock price prediction, P/E is the third most important indicator.Savers want to direct their savings to investment areas where they can get maximum efficiency. This is the most basic feature that a rational investor should have. Stock investors also want to manage their investments with this thought. In this respect, investors conduct detailed research on the sector and stock they plan to invest in. Predictions regarding the possible price formation of the stock in the future is one of these studies. In the finance literature, there are many indicators, ratios, analyzes, indicators and oscillators developed for the future price prediction of the stock. In this study, technical indicators used by licensed professional stock investors were obtained by taking expert opinion. These indicators were conveyed to the experts again to get their opinions with the help of the fuzzy comparison matrix and the experts were asked to compare the variables. The data obtained were analyzed with the Fuzzy Analytical Hierarchy Process (FAHP) method and the technical indicators and ratios used by the experts were listed according to a certain hierarchy. As a result of the analysis, it has been determined that the most important ratio in the stock price estimation process is the MV/BV ratio. While EBIT is the second most important ratio in stock price prediction, P/E is the third most important indicator.

STOCK MARKET FORECASTING USING CONTINUOUS WAVELET TRANSFORM AND LONG SHORT-TERM MEMORY NEURAL NETWORKS

The analysis and exploitation of complex and large-volume data requires new approaches, and modeling it in time series is a very successful technique. A characteristic time series is the one that defines the dynamic financial market and its asset prices. This research presents a novel forecasting methodology, which uses the Continuous Wavelet Transform for the definition of representative elements that define a time series, and a recurrent neural network architecture for the forecast of prices of financial stocks related by the item of income in the short and medium time term. The proposed model, inspired by the Continuous Wavelet Transform and Neural Networks of the "Long short-term memory" type, uses the most representative coefficients of the Wavelet transform based on the time series in the time domain, for the prediction of future prices of stocks in short prospective periods. The results show a very successful projection using this methodology. Future research will analyze the interrelationship presented by the price time series of the same stock market section, in the domain of Wavelets, and how it affects the stock market forecast.

Assessing the economic effects of drought using Positive Mathematical Planning model under climate change scenarios

In recent decades, regions all around the world have experienced severe droughts adversely affecting their agricultural production. Climate change, along with limited access to water will alter future production and agricultural development. The purpose of this study is to provide a perspective for the future cultivation regime in the Divandarre region in the Sepidrood catchment in Iran, using historical climatic, agricultural, and economic information. Future precipitation values are determined for three climate scenarios, then downscaled and converted to pixel-based precipitation maps using the Moving Least Squares method. Future droughts are identified using the Standardized Precipitation Index at 3, 6, and 9-month intervals based on precipitation values and the relationship between different types of droughts (meteorological, agricultural and hydrological). We introduce a new coefficient, the water cost coefficient, derived from drought characteristics that captures the added irrigation cost in drought years because of increased water price. Using the Positive Mathematical Planning method and considering limited land and water, predicted future prices and costs based on a linear regression of supply-demand, and the annual water cost coefficient values, an agroeconomic model is built. After prediction of future price and cost based on historical data from 2005 to 2018, we run future scenarios based on various price and cost values to determine the optimal annual cultivation area for each crop from 2020 to 2040. All scenarios indicate a decline in cultivation area for all crops making agriculture less beneficial in the future. The cultivation regime moves away from more water-consuming products with less economic value (e.g. watermelon) toward less water-consuming, more expensive products (e.g. lentils). The findings of this model along with expert economic judgments help determine the economic effects of climate change on irrigation, farmers' decisions, and water policies, including water markets, and improving irrigation efficiency. Authorities and farmers could adapt to drought shocks and changes in the market while experiencing less revenue loss.

Using a novel clustered 3D-CNN model for improving crop future price prediction

Many research studies used statistics to predict food production, distribution and price trends. Researchers used statistical inference for discovering the relationships of data to build predictive model. However, crop production and its price trend do not only depend on ecosystems, molecular biology, precision agriculture, veterinary science, animal genes, and technology, but also depend on the environmental change and economic factors. Most importantly, the crop price trend is in non-stationary pattern and is influenced by multiple dimensional factors that the traditional techniques of time series forecasting, such as ARIMA, cannot perform well in prediction. Since CNN model can cope with non-stationary data and learn non-linearity by adjusting the model parameters, it can overcome the limitations of the traditional statistical methods in prediction. Therefore, the aims of this research are to conduct a review to identify a more complete factors that may influence crop production and price changes, and to propose a novel Clustered 3D-CNN model for predicting crop future price. The experiments to compare the performance of our proposed model and ARIMA model were done. The average results found that our proposed Clustered 3D-CNN model (MAPE = 0.083, RMSE = 40.39, MAE = 32.31) outperforms the ARIMA model (MAPE = 0.108, RMSE = 59.95, MAE = 46.35). The 3D-CNN model helps decision makers to better predict crop price trend, and to develop a strategic plan for selecting trading partners to reduce the cost and for solving food insecurity problem.

Tingkat Kepuasan Konsumen terhadap Tanaman Hias di Bursa dan Pelelangan Menggung Forest Art 2 Kecamatan Tawangmangu

<em>Consumers have an important role in the business world, one of which is the ornamental plant business. Consumer satisfaction was strongly influenced by the level of income, where consumers have a decision in choosing a product they will buy. Knowledge of consumer perceptions is important to increase farmers' income. This research method uses a descriptive approach, where data collection was carried out using interviews and direct surveys. Data were analysed using the Consumer Satisfaction Index (CSI). The level of consumer satisfaction with ornamental plants on the stock exchange and the auction of ornamental plants at Menggung Forest Art 2 was classified into the very satisfied category. Consumer satisfaction with ornamental plants is influenced by attributes such as variety, level of product uniqueness, product prices, future price predictions, and the appearance of plants in pots. Improvements regarding the selection of pots that are more adapted to the size of the plant and the selection of pot colours need to be made by traders or ornamental plant auctioneers.</em>

Development of Modern Approaches to Exchange-Traded Financial Asset Evaluation

Estimation of exchange-traded financial asset fair value is one of the most important tasks in modern financial science. However, the importance of methods for prediction of future prices is constantly changing. The study provides a comparative analysis of fundamental and technical analysis methods, reveals their advantages and disadvantages. Such characteristics of fundamental analysis as profit, income, profitability and the level of debt burden are considered in detail, the degree of their influence on the price of securities is analyzed. After the study, conclusions were drawn about the increasingly narrow use of technical analysis during short-term and investment problem solution. A prediction is given for a further decrease of fundamental analysis importance as the main method of assessment. To obtain these conclusions, we used statistical data reflecting the dynamics of exchange-traded assets when companies entered IPOs. The data obtained indicate a clear correlation between the innovation component of a business, market share and its price. At the same time, the company profit has finally ceased to be the main characteristic of the business during its assessment. Additionally, they studied the relationship between the fairness of exchange-traded asset evaluation and quantitative easing (QE) programs. Conclusions are made about the need to increase the forecast prices in the case of a soft monetary policy application.

Research on the Three-Stage Trading Strategy of Gold and Bitcoin Using Technical Indicators and A LSTM Model

In recent years, in pursuit of higher returns, people began to try the combination of bitcoin and gold. This study explored how to use the current and past prices of gold and bitcoin to get the best investment strategies for the next day to get the maximum return. The obtained historical price data of gold and bitcoin from 2016 to 2021 are divided into three stages according to the time axis, namely, stage Ⅰ (1st day-300th day), stage Ⅱ (300th day-400th day) and stage III (400th day-1825th day). Different methods are used for each stage to determine the trading strategy. In stage I, a comprehensive index is constructed by using four technical indexes closely related to the formulation of daily strategies in the financial market, such as moving average convergence and divergence, deviation rate, stochastic index and detrended price oscillator, and the trading strategy is determined by using this comprehensive index. In stage II, the four technical indicators and product prices in stage I are used as training sets, and the daily trading strategy is given by using the decision tree classification model. In the third stage, the long-term and short-term memory neural network is used to develop the future price prediction model of gold and bitcoin, and the trading strategies of gold, bitcoin and cash asset portfolios are formulated according to the dynamic optimization results of different types of traders' risk tolerance. The results show that during the five years from September 11, 2016 to September 10, 2021, the whole strategy created a net profit of $170,381 for aggressive traders and $7,694 for rational traders. After verification, our strategy is effective and robust, and its volatility is relatively small. The research provides theoretical guidance for investors on how to choose portfolios and trade to get the maximum return.

Machine Learning Model Approaches for Price Prediction in Coffee Market using Linear Regression, XGB, and LSTM Techniques

Investors and other business persons have a desire to know about the future market price because, if the investors know about the future price of a certain commodity or stock it will help them to make appropriate business decisions and they can also get profit out of their investment. There are many previous researches that has been done on stock market predictions but there is no related research that has been done on Ethiopia commodity exchange (ECX). Performing future price prediction with better accuracy and performing comparative analysis between the algorithms for two of Ethiopia commodity exchange (ECX) items which are Coffee and Sesame as the research key objectives. Three different types of prediction algorithms to predict the future price, such as Linear Regression (LR), Extreme Gradient Boosting (XGB), Long Short-Term Memory (LSTM) was utilized. There are limited researches worked on price prediction of ECX items specifically, the idea of the price prediction on different Stock markets like New York stock market Exchange and other commodity market items prediction in order to develop our research in ECX was presented. The study apart from predicting the future price, comparative analysis was implemented between the prediction algorithms that we used based on their performance. Two different datasets from ECX: coffee and sesame were used. The reason for the utilization of these datasets is, the commodity items are the largest export items in Ethiopia which makes them very important for Ethiopian economy, and the different datasets helps us to get the advantage of evaluating the algorithms with different number of datasets, since sesame dataset has 7205 instances and coffee dataset has 1540 instances and both of them has 11 attributes. We build an android application in order two implement our algorithms on mobile applications and see if it is possible to implement the prediction algorithms on mobile platforms and make it easy and accessible to users. We call this mobile application Ethiopia Coffee Prices Predictor (ECPP). This application will be used to display the prediction result of Ethiopia Coffee price for short period and it is designed in the way to be user friendly. The programming environment used to implement the prediction algorithms is python, java programming language to design our android application and we used PHP to implement the API, and finally we used MySQL database in order to store information’s online and make them accessible everywhere.

Forecasting of Indian Stock Market Using Rough Set and Fuzzy-Rough Set Based Models

ABSTRACT Rough Set models are being practiced for several decades for dealing with vagueness and uncertainty in data. The present paper explores its applicability in forecasting future stock market prices of Indian companies. In this work, Rough Set and Fuzzy-Rough Set are used as feature selection techniques in conjunction with CN2 algorithm for the generation of rules for future price prediction. Prediction in the present model is in the form of trinary classification, namely it will increase or decrease or will undergo marginal change. Our experiments suggest that the proposed technique performs significantly better than several popular classification algorithms, namely, Support Vector Machines, Random Forest, Artificial Neural Networks, Gaussian Naïve Bayes and ARIMA.

The Interplay Between Investor Activity on Virtual Investment Community and the Trading Dynamics: Evidence From the Bitcoin Market

Virtual investment community has become an important information source for investors. This study contributes to the related literature by investigating the endogenous interplay between investor activity on the virtual investment community and the market trading dynamics using a vector autoregressive framework to analyze an hourly dataset collected from the Bitcoin market. The main results suggest that the sentiment and the posting frequency of virtual investment community messages are largely driven by the past market outcomes, but they provide limited value-relevant information for future price prediction. It is also demonstrated that when investors express conflicting opinions, or when their discussions exhibit a lack of diversity, their incentive to trade decreases, resulting in low trading volume. Theoretical contributions and practical implications are discussed.