Price Prediction Research Articles

Predicting wholesale edible oil prices through Gaussian process regressions tuned with Bayesian optimization and cross-validation

PurposeDeveloping price forecasts for various agricultural commodities has long been a significant undertaking for a variety of agricultural market players. The weekly wholesale price of edible oil in the Chinese market over a ten-year period, from January 1, 2010 to January 3, 2020, is the forecasting issue we explore.Design/methodology/approachUsing Bayesian optimisations and cross-validation, we study Gaussian process (GP) regressions for our forecasting needs.FindingsThe produced models delivered precise price predictions for the one-year period between January 4, 2019 and January 3, 2020, with an out-of-sample relative root mean square error of 5.0812%, a root mean square error (RMSEA) of 4.7324 and a mean absolute error (MAE) of 2.9382.Originality/valueThe projection’s output may be utilised as stand-alone technical predictions or in combination with other projections for policy research that involves making assessment.

An exploration of shipbuilding price prediction for container ships: An integrated model application of deep learning

Shipbuilding price forecasts are key to the maritime industry's foresight, cost management, and competitive edge. This study fills a gap in the existing theoretical and empirical literature on shipbuilding price forecasting by collecting and analyzing weekly price data from October 4, 1996 to September 30, 2022, covering 17,641 observations. The study employs a CNN-BILSTM-AM model, which combines a CNN, BILSTM, AM, for shipbuilding price prediction. The findings suggest that this ensemble model effectively captures the non-linear and time-varying characteristics of shipbuilding price fluctuations. It demonstrates good adaptability to random sample selection, data frequency, and structural disruptions in the sample. This model boasts an impressive predictive accuracy, with an R 2 value of 94.3 %, surpassing many standalone, composite, and traditional forecasting approaches. This study proposes a CNN-BILSTM-AM integrated model that significantly improves the shipbuilding price prediction accuracy and extends the application of machine learning in shipping economics. This study furnishes decision-support and risk management tools, utilizing historical big data to forecast shipbuilding prices, tailored for governments, financial institutions, the shipbuilding industry, and the global shipping industry.

Property Valuation: Using Machine Learning for Rent Value Prediction

The rising demand for rental spaces, such as hotel lodging rooms, has led property owners in high-potential areas to begin renting out their properties to meet this need. The Directorate General of State Assets (DJKN) under the Ministry of Finance, which manages state-owned assets, oversees approximately 1,100 room units with potential for rental. In alignment on increasing non-tax state revenue from state-owned assets (BMN), offering lodging room rentals as a form of BMN utilization presents a promising opportunity for expansion. To facilitate efficient rental services for these BMN rooms, a quick and accurate valuation process is essential. However, establishing fair rental prices for both property owners and tenants poses a significant challenge. This study, therefore, aims to develop automated valuation model (AVM). Since rental price predictions depend on various bebas variabels, the study employs several machine learning algorithms, including Ridge, Linear Regression, Random Forest (RF), Lasso, SVR, Elastic Net, and Extreme Gradient Boosting. The research focuses on rental markets in Jakarta, Bogor, and Bandung, using a dataset of fewer than 500 rental room samples sourced from marketplaces. These data points are adjusted for state-owned asset variabels, followed by feature engineering. The performance of the various algorithms is then compared. The results indicate that the best-performing model and the most important features vary by city, but overall, the Random Forest model delivers strong performance, with room size, road width, and room quality emerging as the most influential factors.

Stock Price Prediction System LSTM Based on Deep Learning

Stock price prediction is a highly complex task due to the inherent volatility and non-linear patterns of financial markets. Recent advancements in deep learning, particularly Long Short-Term Memory (LSTM) networks, have yielded promising results in time series forecasting. This paper provides an in-depth analysis of LSTM models applied to the stock price prediction of major technology companies, including Apple (AAPL), Tesla (TSLA), Microsoft (MSFT), and Nvidia (NVDA). The study utilizes historical stock data to train and evaluate LSTM models, comparing their performance against various other regression models such as Linear Regression, Support Vector Regression (SVR), Decision Tree Regression, and Gradient Boosting Decision Trees (GBDT).The results demonstrate that the LSTM model outperforms traditional models, particularly in its ability to capture long-term dependencies and manage complex, volatile stock data. Among the companies analyzed, the LSTM model achieved the most accurate predictions for Apple, as indicated by the lowest Mean Squared Error (MSE). Tesla's predictions, while less accurate due to high volatility, still showed improvement compared to other models. In conclusion, the LSTM network proved to be the most effective method for stock price prediction in this study, particularly excelling in forecasting long-term trends and reducing prediction errors for volatile stocks.

A novel incremental ensemble learning for real-time explainable forecasting of electricity price

The development of a stable, safe, secure and sustainable energy future is a challenge for all countries these days. In terms of electricity price, its volatile nature makes its prediction a complex task. A precise real-time forecast of the electricity price can have significant consequences for the economy and risks faced. This work presents a new ensemble learning algorithm for making real-time predictions of electricity price in Spain. It combines long and short-term behavior patterns following an online incremental learning approach, keeping the model always up to date. The detection of novelties and unexpected behaviors in the time series streams allows the algorithm to provide more accurate predictions than the reference machine learning algorithms with which it is compared. In addition, the proposed algorithm predicts in real-time and the predictions obtained are interpretable, thus contributing to the Explainable Artificial Intelligence.

Penerapan Model Indeks Tunggal dalam Menganalisis Portofolio Saham Optimal dan Peramalan Harga Saham Optimal Menggunakan Long Short-Term Memory

Investors in choosing stocks are not only on one type of stock, but can diversify. In this study, Blue Chip stocks were used which was carried out in two stages. The first stage is the Single Index Model to obtain an optimal stock portfolio. The second stage, the optimal share price results from the Single Index Model, namely Bank Mandiri (Persero) Tbk (BMRI), is followed by a forecasting process using Long Short-Term Memory (LSTM). The purpose of this study is to apply the Single Index Model to analyze the portfolio on Blue Chip stocks, forecast the selected optimal stock price in the next day, and evaluate the results of the selected optimal stock price forecasting. In the first stage, the Single Index Model uses data for the period from February 1, 2021 to February 1, 2024. The second stage, forecasting with LSTM uses data for the period from February 1, 2021 to February 29, 2024. The results of the first stage were obtained with optimal shares of 13 shares out of 41 Blue Chip shares. The most optimal stock was obtained by BMRI shares. The second stage is the use of BMRI shares with LSTM forecasting. The results of the second stage were obtained by forecasting the stock price performance with the best performance, so that it shows that the stock price performance on March 1, 2024 was obtained of IDR 6894,574. The accuracy of forecasting stock price performance with MAPE is 4.23%. It can be said that the forecast of stock price performance has very good accuracy.

Hybrid Preprocessing for Neural Network-Based Stock Price Prediction

In the domain of stock price prediction, the intricate interdependencies within multivariate time series data present significant challenges for accurate forecasting. This paper introduces a groundbreaking hybrid preprocessing technique to tackle this issue. By leveraging the Empirical Wavelet Transform (EWT), we adeptly extract both low-frequency and high-frequency components from the time series. We then apply Dynamic Time Warping (DTW) and Differential Dynamic Time Warping (DDTW) to measure component similarities, identifying correlated patterns within the stock price series. High-frequency components are managed using sliding windows and Principal Component Analysis (PCA), while PCA is directly applied to low-frequency components. Integrating these techniques into neural network models, our approach yields a substantial 30% improvement in prediction accuracy compared to traditional methods. This significant advancement underscores the potential of our hybrid preprocessing method in enhancing stock price prediction accuracy, offering valuable insights for financial market analysis.

Interval price predictions for coal using a new multi-scale ensemble model

Interval price predictions for coal using a new multi-scale ensemble model

Efficient Integration of CNN and LSTM for Data Mining Observation Algorithms: A Systematic Review

An extensive analysis of the combination of Long Short-Term Memory (LSTM) networks with Convolutional Neural Networks (CNN) is presented in this research. within data mining applications. CNNs, optimized for spatial data processing, and LSTMs, made to manage data in a sequential fashion, are combined to leverage their respective strengths in feature extraction and temporal pattern recognition. By analyzing over 60 published studies, we evaluate the effectiveness of CNN-LSTM models across diverse domains such as medical image analysis, financial time series forecasting, stock price prediction, and sentiment analysis. The review reveals that CNN-LSTM hybrids significantly outperform traditional methods in activities requiring both temporally and spatially understanding. However, challenges such as model interpretability, hyperparameter optimization, and the need for diverse datasets remain. Future research should focus on optimizing these models for specific applications, improving scalability, and addressing limitations like data scarcity. This review underscores the significant potential of CNNLSTM integration in advancing data mining techniques and solving complex problems in various fields. We present the related work of some of the most important publication in the field and classify over 60 published papers from different perspective. This review intends to classify the major techniques, methods, algorithms in the domain of medical images, financial time series analysis, stock price and social media.

Integration of Technical Analysis and Machine Learning to Improve Stock Price Prediction Accuracy

Integration of Technical Analysis and Machine Learning to Improve Stock Price Prediction Accuracy

Hybrid metaheuristic algorithm methods and econometric models in prediction of dogecoin price

Purpose This paper aims to predict Dogecoin price by using artificial intelligence (AI) methods and comparing the results with the econometrics models. Design/methodology/approach An artificial neural network (ANN) was applied as a prediction method without any optimization techniques. Additionally, the genetic algorithm (GA) is used to select the most appropriate input variables. Additionally, based on the literature review and the relationships between crypto-price and global indices, 20 economic indicators, such as Coinbase Bitcoin, Coinbase Litecoin and US dollars, along with main global stock indices such as FTSE100 and NIFTY50, are identified as input variables for the model. Lichtenberg algorithm (LA) and aquila optimization (AO) algorithm are used to make the ANN more robust. To validate our algorithms, they have been implemented on daily data for the last three years. To demonstrate the superiority of the models over traditional methods such as econometrics, regression analysis and curve fitting techniques are used. The effectiveness of these models is then evaluated and compared using criteria such as recall, accuracy and precision. Findings The results indicate that AI-based algorithms not only enhance the accuracy, recall and precision of calculations but also expedite the process without requiring the numerous and restrictive assumptions associated with time series and econometric models. Originality/value The main contribution of this paper is the application of novel approaches such as AO and LA to improve the predictive capabilities of the ANN method for various cryptocurrencies’ prices. It demonstrates the superiority of the proposed algorithms over traditional econometric models using real-life data.

Multistep Brent oil price forecasting with a multi-aspect aeta-heuristic optimization and ensemble deep learning model

Accurate crude oil price forecasting is crucial for various economic activities, including energy trading, risk management, and investment planning. Although deep learning models have emerged as powerful tools for crude oil price forecasting, achieving accurate forecasts remains challenging. Deep learning models’ performance is heavily influenced by hyperparameters tuning, and they are expected to perform differently under various circumstances. Furthermore, price volatility is also sensitive to external factors such as world events. To address these limitations, we propose a hybrid approach that integrates metaheuristic optimisation with an ensemble of five widely used neural network architectures for time series forecasting. Unlike existing methods that apply metaheuristics to optimise hyperparameters within the neural network architecture, we exploit the GWO metaheuristic optimiser at four levels: feature selection, data preparation, model training, and forecast blending. The proposed approach has been evaluated for forecasting three-ahead days using real-world Brent crude oil price data, and the obtained results demonstrate that the proposed approach improves the forecasting performance measured using various benchmarks, achieving 0.000127 of MSE.

Algorithm-Driven Hedonic Real Estate Pricing – An Explainable AI Approach

AbstractData-driven machine learning algorithms triggered a fundamental change in hedonic real estate pricing. However, their adaptive nonparametric structure makes inference and out-ofsample prediction challenging. This study introduces an explainable approach to interpreting machine learning predictions, which has not been done before in the local market context. Specifically, Random Forest and Extreme Gradient Boosting models are developed for residential real estate price prediction in Warsaw in 2021 on 10,827 property transactions. Model-agnostic Explainable Artificial Intelligence (XAI) methods are then used to investigate the black box decision making. The results show the practicability of applying XAI frameworks in the real estate market context to decode the rationale behind data-driven algorithms. Information about the relationships between input variables is extracted in greater detail. Accurate, reliable and transparent real estate valuation support tools can offer substantial advantages to participants in the real estate market, including banks, insurers, pension and sovereign wealth funds, as well public authorities and private individuals.

Predicting multi-frequency crude oil price dynamics: Based on MIDAS and STL methods

Accurate prediction of crude oil prices is important for national energy security and socioeconomic development. Research on crude oil price forecasting has primarily focused on the overall price, overlooking the differentiated investment needs of different entities. To solve this problem, we introduce the Seasonal and Trend decomposition using Loess (STL) method into the Mixed Data Sampling (MIDAS) model. This enables us to more accurately analyze the predictive capability of predictors for crude oil prices at different frequencies. Selected predictors include the Dow Jones Index, US Dollar exchange rate, economic policy uncertainty, related crude oil and energy prices, carbon asset prices, and investor attention. Empirical results indicate that these predictors significantly enhance the forecasting accuracy across all components, with the strongest impact in the trend component. Interestingly, a lag effect is observed in the predictors' impact on the seasonal and residual components, but not on the trend component. Moreover, we calculate the duration of each predictor's effectiveness for different components of crude oil prices, distinguishing short-term and long-term effective predictors. This research offers novel insights into the design of crude oil price forecasting models, which is crucial for enhancing investor returns and maintaining stability in the energy market.

Application and Performance Comparison of Compound Neural Network Model based on CNN Feature Extraction in House Price Forecast

Abstract. This study used a total of eight machine learning algorithms to forecast property prices, it not only provides a robust comparison of the predictive power of different algorithms but also significantly advances our understanding of the factors that influence property prices. In this paper, four traditional machine learning algorithms and four neural network models are selected for comparative study and analysis, of which the neural network models include fully connected neural networks (FCNN), convolutional fully connected neural networks (FCNN+CNN), generative adversarial fully connected networks (FCNN+GANs) and generative adversarial convolutional fully connected neural networks (FCNN+GANs+CNN). This study applied to a Kaggle's sample. The results reveal that the models based on FCNN+CNN and FCNN+GANs+CNN perform relatively well in house price prediction, with both obtaining an explanatory power of R as high as 0. 96 and 0. 97, respectively and significantly outperforming traditional machine learning algorithms. It is worth mentioning that the FCNN+CNN model is slightly stronger in terms of error minimization, but both perform better in terms of stability and generalization capabilities. The conclusion is that neural network models generally have better results than traditional algorithms in house price prediction, and the neural network model of CNN composite has significantly better prediction performance.

Informer-Based Method for Stock Intraday Price Prediction

As a component of the capital market, the stock market plays a very important role in economic development. How to predict the stock price more accurately is the key concern of researchers and investors. To solve the above problems, this paper proposes an Informer based method for stock intraday price prediction. Informer based on attention mechanism can efficiently capture precise long-range dependencies between input and output to increase the prediction capacity. In this research, historical K-line data of traditional securities in China’s financial market are collected. Based on this data set, the intraday stock price prediction performance of Informer and Long Short-Term Memory neural network (LSTM) is compared. The experiment also uses the three-day K-line model to perform pattern recognition on the K-line data of candidate stocks. The results show that the prediction performance of Informer is significantly higher than that of LSTM, and the data information after three-day K-line pattern recognition can improve the prediction accuracy of Informer and reduce time and space overhead of Informer.

Bitcoin price movement prediction by news sentiment using machine learning approach

This study investigates the potential of news sentiment, derived from Google News, in predicting Bitcoin price movements. It explores the correlation between sentiment in news headlines and Bitcoin's market behavior. Employing a data set of news headlines related to Bitcoin from Google News, this research applies sentiment analysis and various machine learning algorithms, including Decision Tree, Random Forest, Logistic Regression, Support Vector Machine, Naïve Bayes, and KNN. The approach involves extracting sentiment scores and correlating these with historical Bitcoin price data. The analysis revealed that Decision Tree and Random Forest algorithms provide a balanced prediction for Bitcoin price movements. Logistic Regression and Support Vector Machine showed high AUC scores but with unbalanced class predictions. Naïve Bayes and KNN were less effective. Overall, sentiment analysis of news headlines can predict short-term Bitcoin price movements to a reasonable degree. This research offers a novel tool for investors and market analysts, enhancing understanding of the impact of news sentiment on cryptocurrency prices. It provides a predictive model to assist in investment decision-making and market analysis. This study contributes to the literature on financial forecasting by integrating sentiment analysis with machine learning for cryptocurrency price prediction. It's one of the few studies to analyze the impact of news sentiment on Bitcoin price, offering a new perspective in the realm of financial technology and digital currencies.

Comparison of Multiple Linear Regression and Random Forest Regression Models for House Price Prediction in Semarang City Using the CRISP-DM Method

The population density in Semarang City is increasing every year. This requires more potential land to build houses to accommodate the denser population. There are various kinds of house prices based on specifications in Semarang City. This requires the right prediction to get the desired house. This study implements and compares the performance of Multiple Linear Regression (MLR) and Random Forest Regression (RFR) models to predict house prices in Semarang City. The method used in this research is CRISP-DM (Cross-Industry Standard Process for Data Mining) as a data mining process. The data used in this research amounted to 9533 data with 8 variables obtained by web scraping. The data will go through a data preprocessing process then training the model. Next is the evaluation stage, which is carried out to measure the performance of the two models using evaluation metrics, namely R-Squared (prediction accuracy), MSE (Mean Squared Error), and RMSE (Root Mean Squared Error). The results of this study show that the MLR model obtained a prediction accuracy 61.1% with a training and testing data division ratio of 75%: 25%. While the RFR model produces a prediction accuracy 78.4% with a training and testing data division ratio of 90%: 10%. This shows that the RFR model is the best performing model. This research successfully applied the RFR model to the streamlit web framework. The final result of this research is a website that can be used by the public to predict house prices according to criteria in Semarang City.

The State of the Art Electricity Load and Price Forecasting for the Modern Wholesale Electricity Market

In a modern and dynamic electricity market, ensuring reliable, sustainable and efficient electricity distribution is a pillar of primary importance for grid operation. The high penetration of renewable energy sources and the formation of competitive prices for utilities play a critical role in the wider economic development. Electricity load and price forecasting have been a key focus of researchers in the last decade due to the substantial economic implications for both producers, aggregators and end consumers. Many forecasting techniques and methods have emerged during this period. This paper conducts a extensive and analytical review of the prevailing load and electricity price forecasting methods in the context of the modern wholesale electricity market. The study is separated into seven main sections. The first section provides the key challenges and the main contributions of this study. The second section delves into the workings of the electricity market, providing a detailed analysis of the three markets that have evolved, their functions and the key factors influencing overall market dynamics. In the third section, the main methodologies of electricity load and price forecasting approaches are analyzed in detail. The fourth section offers a comprehensive review of the existing literature focusing on load forecasting, highlighting various methodologies, models and their applications in this field. This section emphasizes the advances that have been made in all categories of forecasting models and their practical application in different market scenarios. The fifth section focuses on electricity price forecasting studies, summarizing important research papers investigating various modeling approaches. The sixth section constitutes a fundamental discussion and comparison between the load- and price-focused studies that are analyzed. Finally, by examining both traditional and cutting-edge forecasting methods, this review identifies key trends, challenges and future directions in the field. Overall, this paper aims to provide an in-depth analysis leading to the understanding of the state-of-the-art models in load and price forecasting and to be an important resource for researchers and professionals in the energy industry. Based on the research conducted, there is an increasing trend in the use of artificial intelligence models in recent years, due to the flexibility and adaptability they offer for big datasets, compared to traditional models. The combination of models, such as ensemble methods, gives us very promising results.

A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance Metric

Regression, a supervised machine learning approach, establishes relationships between independent variables and a continuous dependent variable. It is widely applied in areas like price prediction and time series forecasting. The performance of regression models is typically assessed using error metrics such as the Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). However, these metrics present challenges including sensitivity to outliers (notably MSE and RMSE) and scale dependency, which complicates comparisons across different models. Additionally, traditional metrics sometimes yield values that are difficult to interpret across various problems. Consequently, there is a need for a metric that consistently reflects regression model performance, independent of the problem domain, data scale, and outlier presence. To overcome these shortcomings, this paper introduces a new regression accuracy measure based on the Hassanat distance, a non-convex distance metric. This measure is not only invariant to outliers but also easy to interpret as it provides an accuracy-like value that ranges from 0 to 1 (or 0–100%). We validate the proposed metric against traditional measures across multiple benchmarks, demonstrating its robustness under various model scenarios and data types. Hence, we suggest it as a new standard for assessing regression models’ accuracy.