scholarly journals Selection of Machine Learning Models for Oil Price Forecasting: Based on the Dual Attributes of Oil

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Lei Yan ◽  
Yuting Zhu ◽  
Haiyan Wang
Keyword(s):  
Machine Learning ◽  
Crude Oil ◽  
Short Term Memory ◽  
Oil Prices ◽  
Principal Component ◽  
Oil Price ◽  
Locally Linear Embedding ◽  
Short Term ◽  
Crude Oil Prices

Since the commodity and financial attributes of crude oil will have a long-term or short-term impact on crude oil prices, we propose a de-dimension machine learning model approach to forecast the international crude oil prices. First, we use principal component analysis (PCA), multidimensional scale (MDS), and locally linear embedding (LLE) methods to reduce the dimensions of the data. Then, based on the recurrent neural network (RNN) and long-term and short-term memory (LSTM) models, we build eight models for predicting the future and spot prices of international crude oil. From the analysis and comparison of the prediction results, we find that reducing the dimension of the data can improve the accuracy of the model and the applicability of RNN and LSTM models. In addition, the LLE-RNN/LSTM models can most successfully capture the nonlinear characteristics of crude oil prices. When the moving window size is twenty, that is, when crude oil price data are lagging by almost a month, each model can minimize its error, and the LLE-RNN /LSTM models have the best robustness.

scholarly journals Relationship between International Crude Oil Price and Indian Stock Market (NSE)

2011 ◽  
pp. 63-73
Author(s):  
Rajendra Mahunta
Keyword(s):  
Crude Oil ◽  
Global Economy ◽  
Stock Exchange ◽  
Oil Prices ◽  
Oil Price ◽  
Raw Material ◽  
Crude Oil Price ◽  
New Era ◽  
Crude Oil Prices

In this new era of economic growth, the exceptional increase in the crude oil prices is one of the significant developments that affect the global economy. Crude oil is an important raw material used for manufacturing sectors, so that increase in the price of oil is bound to warn the economy with inflationary inclination. The study examine the long-term relationships between CNX NIFTY FIFTY index of National Stock Exchange and crude price by using various econometric test. The surge in crude oil prices during recent years has generated a lot of interest in the relationship between oil price and equity markets. The study covers the period between 01.01.2010 and 31.12.2014 and was performed with data consisting of 1245 days. The empirical results show there was a cointegrated long-term relationship between CNX index and crude price. Granger causality results reveal that there is unidirectional causality exists and crude oil price causes NSE (CNX) but NSE (CNX) does not cause oil price.

scholarly journals Smart System for Detecting Anomalies In Crude Oil Prices Using Long Short-Term Memory

2021 ◽  
Vol 10 (6) ◽  
pp. 3122-3127
Keyword(s):  
Crude Oil ◽  
Short Term Memory ◽  
Oil Prices ◽  
Experimental Result ◽  
Short Term ◽  
Smart System ◽  
Term Memory ◽  
Crude Oil Prices ◽  
Proposed Model ◽  
Long Short Term Memory

Crude oil is leading globally, as it represents roughly about 33% of the total energy consumed globally. It is one of the most significant exchanged resources in the world, oil in one way or the other affects our day to day routines, like transportation, cooking and power, and other numerous petrochemical items going from the things we use to the things we wear. The increment sought after for petroleum derivatives is on a persistent ascent, making it vital for the oil and gas industry to think of new methodologies for further developing activity. This paper presents a smart system for detecting anomalies in crude oil prices. The experimental process of the proposed system is of two phases. The first phase has to do with the pre-processing stage, and the training stage while the second phase of the experiment has to do with the building/training of the Long Short-Term Memory algorithm. The experimental result shows that LSTM model had an accuracy result of 98%. The result further shows that our proposed model is under fitting since the training loss is lesser than the validation loss. The proposed model was saved and was used in detecting anomalies of the crude oil prices ranging from 1990 to 2020.

scholarly journals Crude Oil Price Forecasting Based on Hybridizing Wavelet Multiple Linear Regression Model, Particle Swarm Optimization Techniques, and Principal Component Analysis

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Ani Shabri ◽  
Ruhaidah Samsudin
Keyword(s):  
Principal Component Analysis ◽  
Time Series ◽  
Crude Oil ◽  
Oil Prices ◽  
Principal Component ◽  
Oil Price ◽  
Price Forecasting ◽  
Crude Oil Price ◽  
Swarm Optimization ◽  
Crude Oil Prices

Crude oil prices do play significant role in the global economy and are a key input into option pricing formulas, portfolio allocation, and risk measurement. In this paper, a hybrid model integrating wavelet and multiple linear regressions (MLR) is proposed for crude oil price forecasting. In this model, Mallat wavelet transform is first selected to decompose an original time series into several subseries with different scale. Then, the principal component analysis (PCA) is used in processing subseries data in MLR for crude oil price forecasting. The particle swarm optimization (PSO) is used to adopt the optimal parameters of the MLR model. To assess the effectiveness of this model, daily crude oil market, West Texas Intermediate (WTI), has been used as the case study. Time series prediction capability performance of the WMLR model is compared with the MLR, ARIMA, and GARCH models using various statistics measures. The experimental results show that the proposed model outperforms the individual models in forecasting of the crude oil prices series.

scholarly journals Investigating the Behavior of Iran's Light Crude Oil Price in Short Term

2016 ◽  
Vol 10 (3) ◽  
pp. 45
Author(s):  
Seyed Abdollah Razavi ◽  
Mostafa Salimifar ◽  
Seyed Mahdi Mostafavi ◽  
Mortaza Baky Haskuee
Keyword(s):  
Crude Oil ◽  
Price Volatility ◽  
Oil Prices ◽  
Oil Price ◽  
Crude Oil Price ◽  
Short Term ◽  
Light Crude Oil ◽  
Oil Market ◽  
Oil Price Volatility

<p class="zhengwen">Investigate the causes of changing the oil price and modeling for predicting its volatility has always been one of the most important fields of Iran's economic literature study due to its position in Iran's economy. On the other hand, oil price volatility lead to the difficulty in the development programs. Empirical studies show that oil prices volatility are caused the structural bottlenecks (trade balance bottleneck, budget bottlenecks, etc.) in Iran's economic.<strong></strong></p>Understanding the mechanism of oil prices formation can reduce the risk of oil price volatility and its negative impacts on Iran's economy. With the development of oil bourse and oil futures market, oil market changed the crude oil price formation so that the cash flow between financial markets and oil market will deviant the crude oil price from its long term direction by changing in interest rate in short-term. In this paper, it is investigated the crude oil price deviation from its long-term direction with regard to the relationship between mentioned markets in short-term. For this purpose, Fisher price jump model and Frankel theory will be used for test by using daily time series data of 2005-13 about Iran's light crude oil in different areas (different markets), as well as multivariate GARCH technique method. Also, the results show that the pricing strategy is false signal in the use of Urals crude oil in the determining of crude oil price in the Mediterranean and North West Europe markets.

scholarly journals Dynamics of oil price shocks and emerging stock market volatility: a generalized VAR approach

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Megha Agarwalla ◽  
Tarak Nath Sahu ◽  
Shib Sankar Jana
Keyword(s):  
Crude Oil ◽  
Granger Causality ◽  
Stock Prices ◽  
Stock Price ◽  
Oil Prices ◽  
Oil Price ◽  
Content Type ◽  
Crude Oil Prices ◽  
Time Period

Purpose This study aims to establish the dynamic relationship between international crude oil prices and Indian stock prices represented by the Bombay Stock Exchange (BSE) energy index. Design/methodology/approach Using Johansen’s cointegration test, vector error correction (VEC) model, impulse response function and variance decomposition test the study tries to ascertain the short-term and long-term dynamic association between the oil price shock and the movement of stock price and Granger causality test is applied to find out the nature of causality. Findings Considering vector autoregression estimation, the present study analyzes the relationship between the variables and tries to make a valid conclusion. The result of the co-integration test exhibits the presence of a long-term association between these two macro-economic variables during the period under study. Also, in the short-run VEC Granger causality result reveals that the movement of international crude oil price significantly influences the Indian stock price. Research limitations/implications To get a more robust result the study can be further extended by taking a longer time period with data of shorter time-frequency such as daily or weekly and further by using more sophisticated econometric and statistical tools. Further, the study can be extended to firm-level investigation considering the forward trading concentration with the Indian oil basket. Social implications In today’s globalized era, forecasting of share price movement helps investors in predicting the market and invest accordingly. Through this liquidity of the markets enhance and markets become more active in the global arena. Originality/value This study represents fresh findings in the changing time period the linkage between crude oil prices and stock prices which are of value to the academicians, researchers, policymakers, investors, market regulators, etc.

Determinants of Inflation in Vietnam: A VECM Approach

2015 ◽  
Vol 22 (04) ◽  
pp. 26-50
Author(s):  
Ngoc Tran Thi Bich ◽  
Huong Pham Hoang Cam
Keyword(s):  
Interest Rate ◽  
Crude Oil ◽  
Error Correction ◽  
Budget Deficit ◽  
Oil Prices ◽  
Crude Oil Prices ◽  
Domestic Credit ◽  
Short Run ◽  
The Impact

This paper aims to examine the main determinants of inflation in Vietnam during the period from 2002Q1 to 2013Q2. The cointegration theory and the Vector Error Correction Model (VECM) approach are used to examine the impact of domestic credit, interest rate, budget deficit, and crude oil prices on inflation in both long and short terms. The results show that while there are long-term relations among inflation and the others, such factors as oil prices, domestic credit, and interest rate, in the short run, have no impact on fluctuations of inflation. Particularly, the budget deficit itself actually has a short-run impact, but its level is fundamentally weak. The cause of the current inflation is mainly due to public's expectations of the inflation in the last period. Although the error correction, from the long-run relationship, has affected inflation in the short run, the coefficient is small and insignificant. In other words, it means that the speed of the adjustment is very low or near zero. This also implies that once the relationship among inflation, domestic credit, interest rate, budget deficit, and crude oil prices deviate from the long-term trend, it will take the economy a lot of time to return to the equilibrium state.

scholarly journals Shades between Black and Green Investment: Balance or Imbalance?

2021 ◽  
Vol 13 (9) ◽  
pp. 5024
Author(s):  
 Vítor Manuel de Sousa Gabriel ◽  
María Mar Miralles-Quirós ◽  
José Luis Miralles-Quirós
Keyword(s):  
Risk Factor ◽  
Oil Prices ◽  
Oil Price ◽  
Short Term ◽  
Environmental Indices ◽  
Long Run ◽  
Green Investment ◽  
Bounds Test

This paper analyses the links established between environmental indices and the oil price adopting a double perspective, long-term and short-term relationships. For that purpose, we employ the Bounds Test and bivariate conditional heteroscedasticity models. In the long run, the pattern of behaviour of environmental indices clearly differed from that of the oil prices, and it was not possible to identify cointegrating vectors. In the short-term, it was possible to conclude that, in contemporaneous terms, the variables studied tended to follow similar paths. When the lag of the oil price variable was considered, the impacts produced on the stock market sectors were partially of a negative nature, which allows us to suppose that this variable plays the role of a risk factor for environmental investment.

scholarly journals COVID-19 and Its Impact on the Indian Economy

2021 ◽  
pp. 097226292198912
Author(s):  
Vikas Barbate ◽  
Rajesh N. Gade ◽  
Shirish S. Raibagkar
Keyword(s):  
Oil Prices ◽  
Economic Activities ◽  
Short Term ◽  
Indian Economy ◽  
The Great Depression ◽  
Windfall Gain ◽  
Crude Oil Prices ◽  
Tree Approach ◽  
Silver Lining

Pessimism looms large all over. COVID-19 has been projected as worse than the Great Depression of 1930. Everyday analyst and agency reports are diving into new bottoms of a fall-down in economic activities. Indian economy, however, has a slightly different story to tell at this hour of crisis. The silver lining for the Indian economy comes from a steep fall in the crude oil prices from around $70 per barrel to a record 18 years low of $22 per barrel. This windfall gain can, to some extent, offset the direct losses due to COVID-19. At the same time, dreams like a $5 trillion economy no longer look even a remote possibility. This article takes stock of the likely impact of COVID-19 on the Indian economy in the short term and the long term. A decision-tree approach has been adopted for doing the projections.

Forecasting Crude Oil price using Artificial Neural Network model

2021 ◽  
pp. 321-326
Author(s):  
Sivaprakash J. ◽  
Manu K. S.
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Crude Oil ◽  
Back Propagation ◽  
Oil Prices ◽  
Oil Price ◽  
Back Propagation Algorithm ◽  
Crude Oil Price ◽  
Propagation Algorithm ◽  
Crude Oil Prices

In the advanced global economy, crude oil is a commodity that plays a major role in every economy. As Crude oil is highly traded commodity it is essential for the investors, analysts, economists to forecast the future spot price of the crude oil appropriately. In the last year the crude oil faced a historic fall during the pandemic and reached all time low, but will this situation last? There was analysis such as fundamental analysis, technical analysis and time series analyses which were carried out for predicting the movement of the oil prices but the accuracy in such prediction is still a question. Thus, it is necessary to identify better methods to forecast the crude oil prices. This study is an empirical study to forecast crude oil prices using the neural networks. This study consists of 13 input variables with one target variable. The data are divided in the ratio 70:30. The 70% data is used for training the network and 30% is used for testing. The feed forward and back propagation algorithm are used to predict the crude oil price. The neural network proved to be efficient in forecasting in the modern era. A simple neural network performs better than the time series models. The study found that back propagation algorithm performs better while predicting the crude oil price. Hence, ANN can be used by the investors, forecasters and for future researchers.

Sign in / Sign up

Export Citation Format

Share Document