scholarly journals Forecasting Price of Amazon Spot Instances Using Machine Learning

2021 ◽  
Vol 11 (2) ◽  
pp. 71-82
Author(s):  
Manas Malik ◽  
Nirbhay Bagmar
Keyword(s):  
Machine Learning ◽  
Cloud Model ◽  
Spot Price ◽  
Cloud Provider ◽  
Spot Prices ◽  
Pricing Mechanism ◽  
Availability Factor ◽  
Bid Price ◽  
Hourly Session

An auction-based cloud model is followed in the spot pricing mechanism, where the spot instances charge changes with time. The user is bound to pay for the time that is initially initiated. If the user terminates before the sessional hourly completion, then the customer will be billed on the entire hourly session. In case Amazon terminates the instance then the customer would not be billed for the partial hour. When the current spot price reduces to bid price without any notification the cloud provider terminates the spot instance, it is a big disadvantage to the time of the availability factor, which is highly important. Therefore, it is crucial for the bidder to forecast before engaging the bids for spot prices. This paper represents a technique to analyze and predict the spot prices for instances using machine learning. It also discusses implementation, explored factors in detail, and outcomes on numerous instances of Amazon Elastic Compute Cloud (EC2). This technique reduces efforts and errors for forecasting prices.

scholarly journals Forecasting Natural Gas Spot Prices with Machine Learning

Energies ◽  
2021 ◽  
Vol 14 (18) ◽  
pp. 5782
Author(s):  
Dimitrios Mouchtaris ◽  
Emmanouil Sofianos ◽  
Periklis Gogas ◽  
Theophilos Papadimitriou
Keyword(s):  
Machine Learning ◽  
Natural Gas ◽  
Gaussian Process Regression ◽  
Time Frame ◽  
Spot Price ◽  
Support Vector ◽  
Learning Methods ◽  
Spot Prices ◽  
Explanatory Variables ◽  
Machine Learning Methods

The ability to accurately forecast the spot price of natural gas benefits stakeholders and is a valuable tool for all market participants in the competitive gas market. In this paper, we attempt to forecast the natural gas spot price 1, 3, 5, and 10 days ahead using machine learning methods: support vector machines (SVM), regression trees, linear regression, Gaussian process regression (GPR), and ensemble of trees. These models are trained with a set of 21 explanatory variables in a 5-fold cross-validation scheme with 90% of the dataset used for training and the remaining 10% used for testing the out-of-sample generalization ability. The results show that these machine learning methods all have different forecasting accuracy for every time frame when it comes to forecasting natural gas spot prices. However, the bagged trees (belonging to the ensemble of trees method) and the linear SVM models have superior forecasting performance compared to the rest of the models.

Pricing of Futures Contracts

2018 ◽  
Author(s):  
Timothy A. Krause
Keyword(s):  
Fair Value ◽  
Commodity Futures ◽  
Futures Contracts ◽  
Spot Price ◽  
Futures Prices ◽  
No Arbitrage ◽  
Spot Prices ◽  
Cost Of Carry ◽  
Contract Expiration ◽  
The Cost

This chapter examines the relation between futures prices relative to the spot price of the underlying asset. Basic futures pricing is characterized by the convergence of futures and spot prices during the delivery period just before contract expiration. However, “no arbitrage” arguments that dictate the fair value of futures contracts largely determine pricing relations before expiration. Although the cost of carry model in its various forms largely determines futures prices before expiration, the chapter presents alternative explanations. Related commodity futures complexes exhibit mean-reverting behavior, as seen in commodity spread markets and other interrelated commodities. Energy commodity futures prices can be somewhat accurately modeled as a generalized autoregressive conditional heteroskedastic (GARCH) process, although whether these models provide economically significant excess returns is uncertain.

The Unbiasedness and Hedging Effectiveness in KOSPI200 Futures Market

2007 ◽  
Vol 15 (1) ◽  
pp. 73-100
Author(s):  
Seok Kyu Kang
Keyword(s):  
Risk Management ◽  
Risk Premium ◽  
Futures Market ◽  
Spot Price ◽  
Sample Period ◽  
Futures Prices ◽  
Spot Prices ◽  
Hedging Effectiveness ◽  
Futures Price ◽  
Rolling Windows

This study is to examine the unblasedness hypothesis and hedging effectiveness in KOSPI20() futures market. The unbiasedness and efficiency hypothesis is carried out using a cointegration methodology. And hedging effectiveness is measured by comparing hedging performance of the naive hedge model, OLS hedge model. and constant correlation bivariate GARCH (1. 1) hedge model based on rolling windows. The sample period covers from May. 3. 1996 to December. 8, 2005. The empirical results are summarized as follows: First, there exists the cOintegrating relationship between realized spot prices and futures prices of the 10 day. 22 day. 44 day. and 59 day prior to maturity. Second. futures prices of backward the 10 day. 22 day. 44 day from maturity provide unbiased forecasts of the realized spot prices. The KOSPI200 futures price is likely to predict accurately future KOSPI200 spot prices without the trader having to pay a risk premium for the privilege of trading the contract. Third. for shorter maturity. the futures price appears to be the best forecaster of spot price. Forth, bivariate GARCH hedging effectiveness outperforms the naive and OLS hedging effectiveness. The implications of these findings show that KOSPI200 futures market behaves as unbiased predictor of future spot price and risk management instrument of KOSPI200 spot portfolio.

scholarly journals Information Content of Implicit Spot Prices Embedded in Single Stock Future Prices: Evidence from Indian Market

2017 ◽  
Vol 16 (2) ◽  
pp. 169-187 ◽  
Author(s):  
Rajesh Pathak ◽  
Thanos Verousis ◽  
Yogesh Chauhan
Keyword(s):  
Stock Returns ◽  
Information Content ◽  
Stock Exchange ◽  
Jel Classification ◽  
Spot Price ◽  
Spot Prices ◽  
Pricing Errors ◽  
Pricing Error ◽  
The Difference ◽  
Cost Of Carry

This study examines the information content of pricing error, measured by the difference between the implied price computed using the cost of carry model and the spot price of Single Stock Futures (SSFs), traded on National Stock Exchange (NSE), India. The returns of portfolios, based on ranking of such pricing errors, are investigated. The consistency of results is verified by controlling for established risk factors, that is, market, size, value and momentum premium, and idiosyncratic factors such as firm’s liquidity and size. Our study reveals that the pricing error is a priced risk factor that contains incremental information about stock returns of day t, and not beyond. We conclude that implied spot prices from stock futures market are useful for traders to profit in the spot market. JEL Classification: G120, G130

A Bivariate Model for Deman and Spot Price of Electricity

2012 ◽  
Vol 433-440 ◽  
pp. 3910-3917
Author(s):  
Hilary Green ◽  
Nino Kordzakhia ◽  
Ruben Thoplan
Keyword(s):  
Electricity Markets ◽  
Historical Data ◽  
Extreme Values ◽  
Spot Price ◽  
Bivariate Model ◽  
Spot Prices ◽  
Short Period ◽  
Detailed Statistical Analysis ◽  
Modelling Methodology ◽  
The Mean

In this paper bivariate modelling methodology, solely applied to the spot price of electricity or demand for electricity in earlier studies, is extended to a bivariate process of spot price of electricity and demand for electricity. The suggested model accommodates common idiosyncrasies observed in deregulated electricity markets such as cyclical trends in price and demand for electricity, occurrence of extreme spikes in prices, and mean-reversion effect seen in settling of prices from extreme values to the mean level over a short period of time. The paper presents detailed statistical analysis of historical data of daily averages of electricity spot prices and corresponding demand for electricity. The data is obtained from the NSW section of Australian Energy Markets.

scholarly journals The Impact of Futures Price Volatility to Spot Market : Case of Coffee in Indonesia

2019 ◽  
Vol 15 (1) ◽  
pp. 1-15 ◽  
Author(s):  
Anis Erma Wulandari ◽  
Harianto Harianto ◽  
Bustanul Arifin ◽  
Heny K Suwarsinah
Keyword(s):  
Exchange Rate ◽  
Price Volatility ◽  
Spot Market ◽  
Futures Market ◽  
Spot Price ◽  
Price Risk ◽  
Price Inflation ◽  
Spot Prices ◽  
Futures Price ◽  
The Impact

Indonesia is the world 4th largest coffee producer after Brazil, Vietnam and Colombia with export potential and higher national consumption concluded in 2017 while the coffee production was relatively stagnant. This was led the producer to not only the production risk but also the price risk which then emphasize the importance of futures markets existence as price risk management. This study is performed to examine the impact of futures price volatility to spot market using ARCH-GARCH toward primary data of coffee futures and spot prices of 1172 trading days starting from January 2014 to June 2018. The ARCH-GARCH analysis result indicates that futures price volatility and monetary variables are impacting the volatility of spot price. Arabica spot price volatility is impacted by volatility of Arabica futures price, inflation and exchange rate while Robusta spot price is impacted by Robusta futures price volatility and exchange rate. This is confirming that futures market plays dominant role in spot price discovery. Local futures and spot prices are also found to be significantly influenced by volatility of offshore futures prices which indicates that emerging country futures market is actually influenced by offshore futures market which the price itself used as price reference.

scholarly journals Gold Exchange Traded Fund - Price Discovery and Performance Analysis

2018 ◽  
Vol 65 (4) ◽  
pp. 477-495
Author(s):  
Mathew Mallika ◽  
M. M. Sulphey
Keyword(s):  
Price Discovery ◽  
Tracking Error ◽  
Spot Price ◽  
Exchange Traded Funds ◽  
Vector Error Correction ◽  
Spot Prices ◽  
Deviation Analysis ◽  
Vector Error ◽  
And Performance ◽  
Exchange Traded Fund

Abstract The paper aims to examine the price discovery process and the performance of Gold Exchange Traded Funds especially with respect to two Gold ETFs, namely, Goldman Sachs Gold Exchange Traded Scheme (GoldBeEs) and SBI Gold Exchange Traded Scheme (SBIGETS), for the period 2009 – 2016. The study has employed Johansen cointegration and Johansen’s Vector Error Correction Model (VECM) for the price discovery analysis. The results of VECM reveal that the spot prices lead the Gold ETFs price during the study period. Tracking Error analysis shows that Gold ETFs have neither outperformed nor underperformed the spot price. Price Deviation analysis indicates that Gold ETFs are trading on an average lower than the spot price of gold. The entire analysis reveals that although the price discovery takes place in the spot market, Gold ETFs have performed as well as physical gold and the slight difference in price with that of Gold is only because of certain fees, which are applicable in the management of Gold ETFs.

An Empirical Analysis on Change in Price Discovery of KOSPI200 Futures Through Market Maturity Process

2006 ◽  
Vol 14 (2) ◽  
pp. 51-77
Author(s):  
Woo–baik Lee
Keyword(s):  
Error Correction ◽  
Trading Volume ◽  
Price Discovery ◽  
Futures Market ◽  
Spot Price ◽  
Sample Period ◽  
Information Share ◽  
Spot Prices ◽  
Intraday Data ◽  
Arbitrage Opportunity

This paper estimates the contribution of KOSPI200 futures to spot price discovery based on methodology of ‘information share’, which is suggested by Hasbrouck (1995). Using the intraday data covering sample period from year 1997 to 2003, I estimate information share with specification of Vector Error Correction Model. Main empirical findings are summarized as followings; First. estimate of information share is above 60 percent on average through-out the entire sample period. Second. the contribution of KOSPI200 futures to error correction increased during the recent year of sample period. showing that futures price have strong tendency to lead the spot price. Third. price discovery of KOSPI200 futures have significantly positive relationship with program trading volume and seems to increase under contango. These empirical findings explain the ‘market maturity effect’ that role of futures in spot price discovery enhances as cointegration between futures and spot prices strengthens and futures market countervails the arbitrage opportunity. In general. this paper presents that mature futures market Significantly contributes to spot market efficiency and price discovery process.

Sign in / Sign up

Export Citation Format

Share Document