Search results for: price forecasting

Authors: Michele Catalano, Jacopo Di Domenico, Luca Riccetti, Andrea Teglio

Abstract:

We develop a data-driven agent based model (ABM) for the Italian economy. We calibrate the model for the initial condition and parameters. As a preliminary step, we replicate the Monte-Carlo simulation for the Austrian economy. Then, we evaluate the dynamic properties of the model: the long-run equilibrium and the allocative efficiency in terms of disequilibrium patterns arising in the search and matching process for final goods, capital, intermediate goods, and credit markets. In this perspective, we use a randomized initial condition approach. We perform a robustness analysis perturbing the system for different parameter setups. We explore the empirical properties of the model using a rolling window forecast exercise from 2010 to 2022 to observe the model’s forecasting ability in the wake of the COVID-19 pandemic. We perform an analysis of the properties of the model with a different number of agents, that is, with different scales of the model compared to the real economy. The model generally displays transient dynamics that properly fit macroeconomic data regarding forecasting ability. We stress the model with a large set of shocks, namely interest policy, fiscal policy, and exogenous factors, such as external foreign demand for export. In this way, we can explore the most exposed sectors of the economy. Finally, we modify the technology mix of the various sectors and, consequently, the underlying input-output sectoral interdependence to stress the economy and observe the long-run projections. In this way, we can include in the model the generation of endogenous crisis due to the implied structural change, technological unemployment, and potential lack of aggregate demand creating the condition for cyclical endogenous crises reproduced in this artificial economy.

Keywords: agent-based models, behavioral macro, macroeconomic forecasting, micro data

Procedia PDF Downloads 70

Authors: Yunwei Zhang, Qiaochu Tang, Yao Zhang, Jiabin Wang, Ulrich Stimming, Alpha Lee

Abstract:

Forecasting the state of health and remaining useful life of Li-ion batteries is an unsolved challenge that limits technologies such as consumer electronics and electric vehicles. Here we build an accurate battery forecasting system by combining electrochemical impedance spectroscopy (EIS) -- a real-time, non-invasive and information-rich measurement that is hitherto underused in battery diagnosis -- with Gaussian process machine learning. We collect over 20,000 EIS spectra of commercial Li-ion batteries at different states of health, states of charge and temperatures -- the largest dataset to our knowledge of its kind. Our Gaussian process model takes the entire spectrum as input, without further feature engineering, and automatically determines which spectral features predict degradation. Our model accurately predicts the remaining useful life, even without complete knowledge of past operating conditions of the battery. Our results demonstrate the value of EIS signals in battery management systems.

Keywords: battery degradation, machine learning method, electrochemical impedance spectroscopy, battery diagnosis

Procedia PDF Downloads 149

Authors: Carol Anne Hargreaves

Abstract:

A key issue in stock investment is how to select representative features for stock selection. The objective of this paper is to firstly determine whether an automated stock investment system, using machine learning techniques, may be used to identify a portfolio of growth stocks that are highly likely to provide returns better than the stock market index. The second objective is to identify the technical features that best characterize whether a stock’s price is likely to go up and to identify the most important factors and their contribution to predicting the likelihood of the stock price going up. Unsupervised machine learning techniques, such as cluster analysis, were applied to the stock data to identify a cluster of stocks that was likely to go up in price – portfolio 1. Next, the principal component analysis technique was used to select stocks that were rated high on component one and component two – portfolio 2. Thirdly, a supervised machine learning technique, the logistic regression method, was used to select stocks with a high probability of their price going up – portfolio 3. The predictive models were validated with metrics such as, sensitivity (recall), specificity and overall accuracy for all models. All accuracy measures were above 70%. All portfolios outperformed the market by more than eight times. The top three stocks were selected for each of the three stock portfolios and traded in the market for one month. After one month the return for each stock portfolio was computed and compared with the stock market index returns. The returns for all three stock portfolios was 23.87% for the principal component analysis stock portfolio, 11.65% for the logistic regression portfolio and 8.88% for the K-means cluster portfolio while the stock market performance was 0.38%. This study confirms that an automated stock investment system using machine learning techniques can identify top performing stock portfolios that outperform the stock market.

Keywords: machine learning, stock market trading, logistic regression, cluster analysis, factor analysis, decision trees, neural networks, automated stock investment system

Procedia PDF Downloads 158

Authors: Cinthia C. Costa, Heloisa L. Burnquist, Joaquim J. M. Guilhoto

Abstract:

This study identified the impact of special agricultural safeguards (SSG) for the global market of meat and for the Brazilian economy. The tariff lines subject to SSG were selected and the period of analysis was 1995 (when the rules about the SSGs were established) to 2015 (more recent period for which there are notifications). The value of additional tariff was calculated for each of the most important tariff lines. The import volume and the price elasticities for imports were used to estimate the impacts of each additional tariff estimated on imports. Finally, the effect of Brazilian exports of meat without SSG taxes was calculated as well as its impact in the country’s economy by using an input-output matrix. The most important markets that applied SSGs were the U.S. for beef and European Union for poultry. However, the additional tariffs could be estimated in only two of the sixteen years that the U.S. applied SSGs on beef imports, suggesting that its use has been enforced when the average annual price has been higher than the trigger price level. The results indicated that the value of the bovine and poultry meat that could not be exported by Brazil due to SSGs to both markets (EU and the U.S.) was equivalent to BRL 804 million. The impact of this loss in trade was about: BRL 3.7 billion of the economy’s production value (at 2015 prices) and almost BRL 2 billion of the Brazilian Gross Domestic Product (GDP).

Keywords: beef, poultry meat, SSG tariff, input-output matrix, Brazil

Procedia PDF Downloads 122

Authors: Tarah Bouaricha

Abstract:

The impact of worst natural disasters is analysed in terms of insured losses which happened between 2010 and 2014 on S&P insurance index. Event study analysis is used to test whether natural disasters impact insurance index stock market price. There is no negative impact on insurance stock market price around the disasters event. To analyse the reaction of insurance stock market, normal returns (NR), abnormal returns (AR), cumulative abnormal returns (CAR), cumulative average abnormal returns (CAAR) and a parametric test on AR and on CAR are used.

Keywords: study event, natural disasters, insurance, reinsurance, stock market

Procedia PDF Downloads 396

Authors: Anwar Hasan Abdullah Othman, Ahamed Kameel, Hasanuddeen Abdul Aziz

Abstract:

In this study, an attempt has been made to investigate the relationship specifically the causal relation between fund unit prices of Islamic equity unit trust fund which measure by fund NAV and the selected macro-economic variables of Malaysian economy by using VECM causality test and Granger causality test. Monthly data has been used from Jan, 2006 to Dec, 2012 for all the variables. The findings of the study showed that industrial production index, political election and financial crisis are the only variables having unidirectional causal relationship with fund unit price. However, the global oil prices is having bidirectional causality with fund NAV. Thus, it is concluded that the equity unit trust fund industry in Malaysia is an inefficient market with respect to the industrial production index, global oil prices, political election and financial crisis. However, the market is approaching towards informational efficiency at least with respect to four macroeconomic variables, treasury bill rate, money supply, foreign exchange rate and corruption index.

Keywords: fund unit price, unit trust industry, Malaysia, macroeconomic variables, causality

Procedia PDF Downloads 470

Authors: Pruethipong Xinghatiraj, Rajwanlop Kumpoopong

Abstract:

Considering the current situation of road safety, Thailand has the world’s second-highest road fatality rate. Therefore, decreasing the road accidents in Thailand is a prime policy of the Thai government seeking to accomplish. One of the approaches to reduce the accident rate is to improve road environments to fit with the local behavior of the road users. The Department of Highways ensures that choosing the road median types right to the road characteristics, e.g. roadside characteristics, traffic volume, truck traffic percentage, etc., can decrease the possibility of accident occurrence. Presently, raised median, depressed median, painted median and median barriers are typically used in Thailand Highways. In this study, factors affecting road accident for each median type will be discovered through the analysis of the collecting of accident data, death numbers on sample of 600 Kilometers length across the country together with its roadside characteristics, traffic volume, heavy vehicles percentage, and other key factors. The benefits of this study can assist the Highway designers to select type of road medians that can match local environments and then cause less accident prone.

Keywords: highways, road safety, road median, forecasting model

Procedia PDF Downloads 269

Authors: Gabriele Iannotta

Abstract:

This paper investigates credit cycles by means of an experiment based on a Kiyotaki & Moore (1997) model with heterogeneous expectations. The aim is to examine how a credit squeeze caused by high lender-level risk perceptions affects the real prices of a collateralised asset, with a special focus on the macroeconomic implications of rising price volatility in terms of total welfare and the number of bankruptcies that occur. To do that, a learning-to-forecast experiment (LtFE) has been run where participants are asked to predict the future price of land and then rewarded based on the accuracy of their forecasts. The setting includes one lender and five borrowers in each of the twelve sessions split between six control groups (G1) and six treatment groups (G2). The only difference is that while in G1 the lender always satisfies borrowers’ loan demand (bankruptcies permitting), in G2 he/she closes the entire credit market in case three or more bankruptcies occur in the previous round. Experimental results show that negative risk-driven supply shocks amplify the volatility of collateral prices. This uncertainty worsens the agents’ ability to predict the future value of land and, as a consequence, the number of defaults increases and the total welfare deteriorates.

Keywords: Behavioural Macroeconomics, Credit Cycle, Experimental Economics, Heterogeneous Expectations, Learning-to-Forecast Experiment

Procedia PDF Downloads 125

Authors: Yan Wang, Yasushi Asami, Yukio Sadahiro

Abstract:

In urban context, urban nodes such as amenity or hazard will certainly affect house price, while classic hedonic analysis will employ distance variables measured from each urban nodes. However, effects from distances to facilities on house prices generally do not represent the true price of the property. Distance variables measured on the same surface are suffering a problem called multicollinearity, which is usually presented as magnitude variance and mean value in regression, errors caused by instability. In this paper, we provided a theoretical framework to identify and gather the data with less bias, and also provided specific sampling method on locating the sample region to avoid the spatial multicollinerity problem in three distance variable’s case.

Keywords: hedonic regression, urban node, distance variables, multicollinerity, collinearity

Procedia PDF Downloads 465

Authors: Andrei-Marius Sandu

Abstract:

This study aims to analyze the bovine meat and milk sector for the period 2007-2013. For the period analyzed, it is known that Romania has benefited from EU funding through the National Rural Development Programme 2007-2013. In this programme, there were measures that addressed exclusively the animal husbandry sector in Romania. This paper presents data on bovine production of meat, milk and livestock in Romania, but also data on the price and impact the European Funds implementation had on them.

Keywords: European funds, measures, national rural development programme, price

Procedia PDF Downloads 422

Authors: Ira Joseph

Abstract:

The LNG paradox addresses the issue of how the most expensive form of gas supply, which is LNG, will grow in an end user market where demand is most competitive, which is power generation. In this case, LNG demand growth is under siege from two entirely different directions. At one end is price; it will be extremely difficult for gas to replace coal in Asia due to the low price of coal and the age of the generation plants. Asia's coal fleet, on average, is less than two decades old and will need significant financial incentives to retire before its state lifespan. While gas would cut emissions in half relative to coal, it would also more than double the price of the fuel source for power generation, which puts it in a precarious position. In most countries in Asia other than China, this cost increase, particularly from imports, is simply not realistic when it is also necessary to focus on economic growth and social welfare. On the other end, renewables are growing at an exponential rate for three reasons. One is that prices are dropping. Two is that policy incentives are driving deployment, and three is that China is forcing renewables infrastructure into the market to take a political seat at the global energy table with Saudi Arabia, the US, and Russia. Plus, more renewables will lower import growth of oil and gas in China, if not end it altogether. Renewables are the predator at the gate of gas demand in power generation and in every year that passes, renewables cut into demand growth projections for gas; in particular, the type of gas that is most expensive, which is LNG. Gas does have a role in the future, particularly within a domestic market. Once it crosses borders in the form of LNG or even pipeline gas, it quickly becomes a premium fuel and must be marketed and used this way. Our research shows that gas will be able to compete with batteries as an intermittency and storage tool and does offer a method to harmonize with renewables as part of the energy transition. As a baseload fuel, however, the role of gas, particularly, will be limited by cost once it needs to cross a border. Gas converted into blue or green hydrogen or ammonia is also an option for storage depending on the location. While this role is much reduced from the primary baseload role that gas once aspired to land, it still offers a credible option for decades to come.

Keywords: natural gas, LNG, demand, price, intermittency, storage, renewables

Procedia PDF Downloads 62

Authors: Dongkwon Han, Sangho Kim, Sunil Kwon

Abstract:

Unconventional gas resources have dramatically changed the future energy landscape. Unlike conventional gas resources, the key challenges in unconventional gas have been the requirement that applies to advanced approaches for production forecasting due to uncertainty and complexity of fluid flow. In this study, artificial neural network (ANN) model which integrates machine learning and data-driven approach was developed to predict productivity in shale gas. The database of 129 wells of Eagle Ford shale basin used for testing and training of the ANN model. The Input data related to hydraulic fracturing, well completion and productivity of shale gas were selected and the output data is a cumulative production. The performance of the ANN using all data sets, clustering and variables importance (VI) models were compared in the mean absolute percentage error (MAPE). ANN model using all data sets, clustering, and VI were obtained as 44.22%, 10.08% (cluster 1), 5.26% (cluster 2), 6.35%(cluster 3), and 32.23% (ANN VI), 23.19% (SVM VI), respectively. The results showed that the pre-trained ANN model provides more accurate results than the ANN model using all data sets.

Keywords: unconventional gas, artificial neural network, machine learning, clustering, variables importance

Procedia PDF Downloads 196

Authors: Zane Turner, Kevin Labille, Susan Gauch

Abstract:

Sentiment analysis is a broad and expanding field that aims to extract and classify opinions from textual data. Lexicon-based approaches are based on the use of a sentiment lexicon, i.e., a list of words each mapped to a sentiment score, to rate the sentiment of a text chunk. Our work focuses on predicting stock price change using a sentiment lexicon built from financial conference call logs. We present a method to generate a sentiment lexicon based upon an existing probabilistic approach. By using a domain-specific lexicon, we outperform traditional techniques and demonstrate that domain-specific sentiment lexicons provide higher accuracy than generic sentiment lexicons when predicting stock price change.

Keywords: computational finance, sentiment analysis, sentiment lexicon, stock movement prediction

Procedia PDF Downloads 128

Authors: Zane Turner, Kevin Labille, Susan Gauch

Abstract:

Sentiment analysis is a broad and expanding field that aims to extract and classify opinions from textual data. Lexicon-based approaches are based on the use of a sentiment lexicon, i.e., a list of words each mapped to a sentiment score, to rate the sentiment of a text chunk. Our work focuses on predicting stock price change using a sentiment lexicon built from financial conference call logs. We introduce a method to generate a sentiment lexicon based upon an existing probabilistic approach. By using a domain-specific lexicon, we outperform traditional techniques and demonstrate that domain-specific sentiment lexicons provide higher accuracy than generic sentiment lexicons when predicting stock price change.

Keywords: computational finance, sentiment analysis, sentiment lexicon, stock movement prediction

Procedia PDF Downloads 170

Authors: Oscar Javier Herrera, Manuel Angel Camacho

Abstract:

This paper addresses a cutting edge method of business demand forecasting, based on an empirical probability function when the historical behavior of the data is random. Additionally, it presents error determination based on the numerical method technique ‘propagation of errors’. The methodology was conducted characterization and process diagnostics demand planning as part of the production management, then new ways to predict its value through techniques of probability and to calculate their mistake investigated, it was tools used numerical methods. All this based on the behavior of the data. This analysis was determined considering the specific business circumstances of a company in the sector of communications, located in the city of Bogota, Colombia. In conclusion, using this application it was possible to obtain the adequate stock of the products required by the company to provide its services, helping the company reduce its service time, increase the client satisfaction rate, reduce stock which has not been in rotation for a long time, code its inventory, and plan reorder points for the replenishment of stock.

Keywords: demand forecasting, empirical distribution, propagation of error, Bogota

Procedia PDF Downloads 631

Authors: Pablo Martinez, Emad Mohamed, Osama Mohsen, Yasser Mohamed

Abstract:

Highway and bridge agencies, such as the Ministry of Transportation in Ontario, use the Bridge Condition Index (BCI) which is defined as the weighted condition of all bridge elements to determine the rehabilitation priorities for its bridges. Therefore, accurate forecasting of BCI is essential for bridge rehabilitation budgeting planning. The large amount of data available in regard to bridge conditions for several years dictate utilizing traditional mathematical models as infeasible analysis methods. This research study focuses on investigating different classification models that are developed to predict the bridge condition index in the province of Ontario, Canada based on the publicly available data for 2800 bridges over a period of more than 10 years. The data preparation is a key factor to develop acceptable classification models even with the simplest one, the k-NN model. All the models were tested, compared and statistically validated via cross validation and t-test. A simple k-NN model showed reasonable results (within 0.5% relative error) when predicting the bridge condition in an incoming year.

Keywords: asset management, bridge condition index, data mining, forecasting, infrastructure, knowledge discovery in databases, maintenance, predictive models

Procedia PDF Downloads 191

Authors: Victoria Masi Haruna Karatu, Nik Kamariah Nikmat

Abstract:

In recent times awareness about the environment and green purchase has been on the increase across nations due to global warming. Previous researchers have attempted to determine what actually influences the purchase intention of consumers in this environmentally conscious epoch. The consumers too have become conscious of what to buy and who to buy from in their purchasing decisions as this action will reflect their concern about the environment and their personal well-being. This trend is a widespread phenomenon in most developed countries of the world. On the contrary evidence revealed that only 5% of the populations of Nigeria involve in green purchase activities thus making the country lag behind its counterparts in green practices. This is not a surprise as Nigeria is facing problems of inadequate green knowledge, non-enforcement of environmental regulations, sensitivity to the price of green products when compared with the conventional ones and distrust towards green products which has been deduced from prior studies of other regions. The main objectives of this study is to examine the direct antecedents of green purchase intention (green availability, government regulations, perceived green knowledge, perceived value and green price sensitivity) in Nigeria and secondly to establish the mediating role of perceived behavioral control on the relationship between these antecedents and green purchase intention. The study adopts quantitative method whereby 700 questionnaires were administered to lecturers in three Nigerian universities. 502 datasets were collected which represents 72 percent response rate. After screening the data only 440 were usable and analyzed using structural equation modeling (SEM) and bootstrapping. From the findings, three antecedents have significant direct relationships with green purchase intention (perceived green knowledge, perceived behavioral control, and green availability) while two antecedents have positive and significant direct relationship with perceived behavioral control (perceived value and green price sensitivity). On the other hand, PBC does not mediate any of the paths from the predictors to criterion variable. This result is discussed in the Nigerian context.

Keywords: Green Availability, Green Price Sensitivity, Green Purchase Intention, Perceived Green Knowledge, Perceived Value

Procedia PDF Downloads 427

Authors: Marlen Acosta Alamo, Lisa Manne, Richard Veit

Abstract:

Habitat loss due to land use change is one of the leading causes of biodiversity loss worldwide. This form of habitat loss is a non-random phenomenon since the same environmental factors that make an area suitable for supporting high local biodiversity overlap with those that make it attractive for urban development. We aimed to compare the effect of two non-random habitat loss predictors on the richness, abundance, and rarity of nature-affiliated and human-affiliated North American breeding birds. For each group of birds, we simulated the non-random habitat loss using two predictors: the House Price Index as a measure of the attractiveness of an area for humans and the Normalized Difference Vegetation Index as a proxy for primary productivity. We compared the results of the two non-random simulation sets and one set of random habitat loss simulations using an analysis of variance and followed up with a Tukey-Kramer test when appropriate. The attractiveness of an area for humans predicted estimates of richness loss and increase of rarity higher than primary productivity and random habitat loss for nature-affiliated and human-affiliated birds. For example, at 50% of habitat loss, the attractiveness of an area for humans produced estimates of richness at least 5% lower and of a rarity at least 40% higher than primary productivity and random habitat loss for both groups of birds. Only for the species abundance of nature-affiliated birds, the attractiveness of an area for humans did not outperform primary productivity as a predictor of biodiversity following habitat loss. We demonstrated the value of the House Price Index, which can be used in conservation assessments as an index of the risks of habitat loss for natural communities. Thus, our results have relevant implications for sustainable urban land-use planning practices and can guide stakeholders and developers in their efforts to conserve local biodiversity.

Keywords: biodiversity loss, bird biodiversity, house price index, non-random habitat loss

Procedia PDF Downloads 88

Authors: Deniz Peksen

Abstract:

This thesis aims to predict trend movement of closing price of stock and to maximize portfolio by utilizing the predictions. In this context, the study aims to define a stock portfolio strategy from models created by using Logistic Regression, Gradient Boosting and Random Forest. Recently, predicting the trend of stock price has gained a significance role in making buy and sell decisions and generating returns with investment strategies formed by machine learning basis decisions. There are plenty of studies in the literature on the prediction of stock prices in capital markets using machine learning methods but most of them focus on closing prices instead of the direction of price trend. Our study differs from literature in terms of target definition. Ours is a classification problem which is focusing on the market trend in next 20 trading days. To predict trend direction, fourteen years of data were used for training. Following three years were used for validation. Finally, last three years were used for testing. Training data are between 2002-06-18 and 2016-12-30 Validation data are between 2017-01-02 and 2019-12-31 Testing data are between 2020-01-02 and 2022-03-17 We determine Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate as benchmarks which we should outperform. We compared our machine learning basis portfolio return on test data with return of Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate. We assessed our model performance with the help of roc-auc score and lift charts. We use logistic regression, Gradient Boosting and Random Forest with grid search approach to fine-tune hyper-parameters. As a result of the empirical study, the existence of uptrend and downtrend of five stocks could not be predicted by the models. When we use these predictions to define buy and sell decisions in order to generate model-based-portfolio, model-based-portfolio fails in test dataset. It was found that Model-based buy and sell decisions generated a stock portfolio strategy whose returns can not outperform non-model portfolio strategies on test dataset. We found that any effort for predicting the trend which is formulated on stock price is a challenge. We found same results as Random Walk Theory claims which says that stock price or price changes are unpredictable. Our model iterations failed on test dataset. Although, we built up several good models on validation dataset, we failed on test dataset. We implemented Random Forest, Gradient Boosting and Logistic Regression. We discovered that complex models did not provide advantage or additional performance while comparing them with Logistic Regression. More complexity did not lead us to reach better performance. Using a complex model is not an answer to figure out the stock-related prediction problem. Our approach was to predict the trend instead of the price. This approach converted our problem into classification. However, this label approach does not lead us to solve the stock prediction problem and deny or refute the accuracy of the Random Walk Theory for the stock price.

Keywords: stock prediction, portfolio optimization, data science, machine learning

Procedia PDF Downloads 81

Authors: Muhamad Aris Burhanudin, Angga Firmansyas, Bagus Jaya Santosa

Abstract:

Earthquakes are natural hazard that can trigger the most dangerous hazard, tsunami. 26 December 2004, a giant earthquake occurred in north-west Andalas Island. It made giant tsunami which crushed Sumatra, Bangladesh, India, Sri Lanka, Malaysia and Singapore. More than twenty thousand people dead. The occurrence of earthquake and tsunami can not be avoided. But this hazard can be mitigated by earthquake forecasting. Early preparation is the key factor to reduce its damages and consequences. We aim to investigate quantitatively on pattern of earthquake. Then, we can know the trend. We study about earthquake which has happened in Andalas island, Indonesia one last decade. Andalas is island which has high seismicity, more than a thousand event occur in a year. It is because Andalas island is in tectonic subduction zone of Hindia sea plate and Eurasia plate. A tsunami forecasting is needed to mitigation action. Thus, a Tsunami Forecasting Method is presented in this work. Neutral Network has used widely in many research to estimate earthquake and it is convinced that by using Backpropagation Method, earthquake can be predicted. At first, ANN is trained to predict Tsunami 26 December 2004 by using earthquake data before it. Then after we get trained ANN, we apply to predict the next earthquake. Not all earthquake will trigger Tsunami, there are some characteristics of earthquake that can cause Tsunami. Wrong decision can cause other problem in the society. Then, we need a method to reduce possibility of wrong decision. Fuzzy TOPSIS is a statistical method that is widely used to be decision seconder referring to given parameters. Fuzzy TOPSIS method can make the best decision whether it cause Tsunami or not. This work combines earthquake prediction using neural network method and using Fuzzy TOPSIS to determine the decision that the earthquake triggers Tsunami wave or not. Neural Network model is capable to capture non-linear relationship and Fuzzy TOPSIS is capable to determine the best decision better than other statistical method in tsunami prediction.

Keywords: earthquake, fuzzy TOPSIS, neural network, tsunami

Procedia PDF Downloads 498

Authors: Siddhartha Paul, Debabrata Das

Abstract:

Closed-loop supply chain (CLSC) management focuses on integrating forward and reverse flow of material as well as information to maximize value creation over the entire life-cycle of a product. Bullwhip effect in supply chain management refers to the phenomenon where a small variation in customers’ demand results in larger variation of orders at the upstream levels of supply chain. Since the quality and quantity of products returned to the collection centers (as a part of reverse logistics process) are uncertain, bullwhip effect is inevitable in CLSC. Therefore, in the present study, first, through an extensive literature survey, we identify all the important factors related to forward as well as reverse supply chain which causes bullwhip effect in CLSC. Second, we develop a system dynamics model to study the interrelationship among the factors and their effect on the performance of overall CLSC. Finally, the results of the simulation study suggest that demand forecasting, lead times, information sharing, inventory and work in progress adjustment rate, supply shortages, batch ordering, price variations, erratic human behavior, parameter correcting, delivery time delays, return rate of used products, manufacturing and remanufacturing capacity constraints are the important factors which have a significant influence on system’s performance, specifically on bullwhip effect in a CLSC.

Keywords: bullwhip effect, closed-loop supply chain, system dynamics, variance ratio

Procedia PDF Downloads 164

Authors: Hamid Goharnejad, Amir Hossein Eghbali

Abstract:

Recent investigations have demonstrated the global sea level rise due to climate change impacts. In this study climate changes study the effects of increasing water level in the strait of Hormuz. The probable changes of sea level rise should be investigated to employ the adaption strategies. The climatic output data of a GCM (General Circulation Model) named CGCM3 under climate change scenario of A1b and A2 were used. Among different variables simulated by this model, those of maximum correlation with sea level changes in the study region and least redundancy among themselves were selected for sea level rise prediction by using stepwise regression. One models of Discrete Wavelet artificial Neural Network (DWNN) was developed to explore the relationship between climatic variables and sea level changes. In these models, wavelet was used to disaggregate the time series of input and output data into different components and then ANN was used to relate the disaggregated components of predictors and predictands to each other. The results showed in the Shahid Rajae Station for scenario A1B sea level rise is among 64 to 75 cm and for the A2 Scenario sea level rise is among 90 to 105 cm. Furthermore the result showed a significant increase of sea level at the study region under climate change impacts, which should be incorporated in coastal areas management.

Keywords: climate change scenarios, sea-level rise, strait of Hormuz, forecasting

Procedia PDF Downloads 271

Authors: Yangrae Cho, Jinseok Kim, Yongtae Park

Abstract:

Mobile app service ecosystem has been abruptly emerged, explosively grown, and dynamically transformed. In contrast with product markets in which product sales directly cause increment in firm’s income, customer’s usage is less visible but more valuable in service market. Especially, the market situation with cutthroat competition in mobile app store makes securing and keeping of users as vital. Although a few service firms try to manage their apps’ usage patterns by fitting on S-curve or applying other forecasting techniques, the time series approaches based on past sequential data are subject to fundamental limitation in the market where customer’s attention is being moved unpredictably and dynamically. We therefore propose a new conceptual approach for detecting usage pattern of mobile app service with Hidden Markov Model (HMM) which is based on the dual stochastic structure and mainly used to clarify unpredictable and dynamic sequential patterns in voice recognition or stock forecasting. Our approach could be practically utilized for app service firms to manage their services’ lifecycles and academically expanded to other markets.

Keywords: mobile app service, usage pattern, Hidden Markov Model, pattern detection

Procedia PDF Downloads 337

Authors: Sofia Stoica

Abstract:

In this paper, we use historical data to predict the stock price of a tech company. To this end, we use a dataset consisting of the stock prices in the past five years of ten major tech companies – Adobe, Amazon, Apple, Facebook, Google, Microsoft, Netflix, Oracle, Salesforce, and Tesla. We experimented with a variety of models– a linear regressor model, K nearest Neighbors (KNN), a sequential neural network – and algorithms - Multiplicative Weight Update, and AdaBoost. We found that the sequential neural network performed the best, with a testing error of 0.18%. Interestingly, the linear model performed the second best with a testing error of 0.73%. These results show that using historical data is enough to obtain high accuracies, and a simple algorithm like linear regression has a performance similar to more sophisticated models while taking less time and resources to implement.

Keywords: finance, machine learning, opening price, stock market

Procedia PDF Downloads 194

Authors: Krishang Surapaneni

Abstract:

The goal of this project is to determine how to predict important aspects of options, including the ask price. We want to compare different machine learning models to learn the best model and the best hyperparameters for that model for this purpose and data set. Option pricing is a relatively new field, and it can be very complicated and intimidating, especially to inexperienced people, so we want to create a machine learning model that can predict important aspects of an option stock, which can aid in future research. We tested multiple different models and experimented with hyperparameter tuning, trying to find some of the best parameters for a machine-learning model. We tested three different models: a Random Forest Regressor, a linear regressor, and an MLP (multi-layer perceptron) regressor. The most important feature in this experiment is the ask price; this is what we were trying to predict. In the field of stock pricing prediction, there is a large potential for error, so we are unable to determine the accuracy of the models based on if they predict the pricing perfectly. Due to this factor, we determined the accuracy of the model by finding the average percentage difference between the predicted and actual values. We tested the accuracy of the machine learning models by comparing the actual results in the testing data and the predictions made by the models. The linear regression model performed worst, with an average percentage error of 17.46%. The MLP regressor had an average percentage error of 11.45%, and the random forest regressor had an average percentage error of 7.42%

Keywords: finance, linear regression model, machine learning model, neural network, stock price

Procedia PDF Downloads 77

Authors: Siphat Lim

Abstract:

This study used Autoregressive Distributed Lag (ARDL) approach to cointegration. In the long-run the general price level and exchange rate have a positively significant effect on domestic output. The estimated result further revealed that fiscal stimulus help stimulate domestic output in the long-run, but not in the short-run, while monetary expansion help to stimulate output in both short-run and long-run. The result is complied with the theory which is the macroeconomic policies, fiscal and monetary policy; help to stimulate domestic output in the long-run. The estimated result of the Vector Error Correction Model (VECM) has indicated more clearly that the consumer price index has a positive effect on output with highly statistically significant. Increasing in the general price level would increase the competitiveness among producers than increase in the output. However, the exchange rate also has a positive effect and highly significant on the gross domestic product. The exchange rate depreciation might increase export since the purchasing power of foreigners has increased. More importantly, fiscal stimulus would help stimulate the domestic output in the long-run since the coefficient of government expenditure is positive. In addition, monetary expansion would also help stimulate the output and the result is highly significant. Thus, fiscal stimulus and monetary expansionary would help stimulate the domestic output in the long-run in Cambodia.

Keywords: fiscal policy, monetary policy, ARDL, VECM

Procedia PDF Downloads 432

Authors: Lin-Han Chiang Hsieh, Hsiao-Yi Lin

Abstract:

This study aims to determine the impact of the disclosure of flood potential map on housing prices. The disclosure is supposed to mitigate the market failure by reducing information asymmetry. On the other hand, opponents argue that the official disclosure of simulated results will only create unnecessary disturbances on the housing market. This study identifies the impact of the disclosure of the flood potential map by comparing the hedonic price of flood potential before and after the disclosure. The flood potential map used in this study is published by Taipei municipal government in 2015, which is a result of a comprehensive simulation based on geographical, hydrological, and meteorological factors. The residential property sales data of 2013 to 2016 is used in this study, which is collected from the actual sales price registration system by the Department of Land Administration (DLA). The result shows that the impact of flood potential on residential real estate market is statistically significant both before and after the disclosure. But the trend is clearer after the disclosure, suggesting that the disclosure does have an impact on the market. Also, the result shows that the impact of flood potential differs by the severity and frequency of precipitation. The negative impact for a relatively mild, high frequency flood potential is stronger than that for a heavy, low possibility flood potential. The result indicates that home buyers are of more concern to the frequency, than the intensity of flood. Another contribution of this study is in the methodological perspective. The classic hedonic price analysis with OLS regression suffers from two spatial problems: the endogeneity problem caused by omitted spatial-related variables, and the heterogeneity concern to the presumption that regression coefficients are spatially constant. These two problems are seldom considered in a single model. This study tries to deal with the endogeneity and heterogeneity problem together by combining the spatial fixed-effect model and geographically weighted regression (GWR). A series of literature indicates that the hedonic price of certain environmental assets varies spatially by applying GWR. Since the endogeneity problem is usually not considered in typical GWR models, it is arguable that the omitted spatial-related variables might bias the result of GWR models. By combing the spatial fixed-effect model and GWR, this study concludes that the effect of flood potential map is highly sensitive by location, even after controlling for the spatial autocorrelation at the same time. The main policy application of this result is that it is improper to determine the potential benefit of flood prevention policy by simply multiplying the hedonic price of flood risk by the number of houses. The effect of flood prevention might vary dramatically by location.

Keywords: flood potential, hedonic price analysis, endogeneity, heterogeneity, geographically-weighted regression

Procedia PDF Downloads 290

Authors: S. Sakthivel

Abstract:

Currently, the global economy is based on the hydrocarbon economy, which is referencing the global hydrocarbon industry. Problems of using these fossil fuels (like oil, NG, coal) are emitting greenhouse gases (GHGs) and price fluctuation, supply/distribution, etc. These challenges can be overcome by using clean energy as hydrogen. The hydrogen economy is the use of hydrogen as a low carbon fuel, particularly for hydrogen vehicles, alternative industrial feedstock, power generation, and energy storage, etc. Engineering consulting firms have a significant role in this ambition and green hydrogen value chain (i.e., integration of renewables, production, storage, and distribution to end-users). Typically, the cost of green hydrogen is a function of the price of electricity needed, the cost of the electrolyser, and the operating cost to run the system. This article focuses on economic viability and explores the alluring business scenarios globally. Break-even analysis was carried out for green hydrogen production and in order to evaluate and compare the impact of the electricity price on the production costs of green hydrogen and relate it to fossil fuel-based brown/grey/blue hydrogen costs. It indicates that the cost of green hydrogen production will fall drastically due to the declining costs of renewable electricity prices and along with the improvement and scaling up of electrolyser manufacturing. For instance, in a scenario where electricity prices are below US$ 40/MWh, green hydrogen cost is expected to reach cost competitiveness.

Keywords: green hydrogen, cost analysis, break-even analysis, renewables, electrolyzer

Procedia PDF Downloads 143

Authors: Disha Bhanot, Vinish Kathuria

Abstract:

This study focusses on the issue of distress sale in horticulture sector in India, which faces unique challenges, given the perishable nature of horticulture crops, seasonal production and paucity of post-harvest produce management links. Distress sale, from a farmer’s perspective may be defined as urgent sale of normal or distressed goods, at deeply discounted prices (way below the cost of production) and it is usually characterized by unfavorable conditions for the seller (farmer). The small and marginal farmers, often involved in subsistence farming, stand to lose substantially if they receive lower prices than expected prices (typically framed in relation to cost of production). Distress sale maximizes price uncertainty of produce leading to substantial income loss; and with increase in input costs of farming, the high variability in harvest price severely affects profit margin of farmers, thereby affecting their survival. The objective of this study is to model the occurrence of distress sale by tomato cultivators in the Indian state of Maharashtra, against the background of differential access to set of factors such as - capital, irrigation facilities, warehousing, storage and processing facilities, and institutional arrangements for procurement etc. Data is being collected using primary survey of over 200 farmers in key tomato growing areas of Maharashtra, asking information on the above factors in addition to seeking information on cost of cultivation, selling price, time gap between harvesting and selling, role of middleman in selling, besides other socio-economic variables. Farmers selling their produce far below the cost of production would indicate an occurrence of distress sale. Occurrence of distress sale would then be modelled as a function of farm, household and institutional characteristics. Heckman-two-stage model would be applied to find the probability/likelihood of a famer falling into distress sale as well as to ascertain how the extent of distress sale varies in presence/absence of various factors. Findings of the study would recommend suitable interventions and promotion of strategies that would help farmers better manage price uncertainties, avoid distress sale and increase profit margins, having direct implications on poverty.

Keywords: distress sale, horticulture, income loss, India, price uncertainity

Procedia PDF Downloads 245

Authors: Nazaitul Idya Hamzah, Muhammad Syafiq Mazli, Maszatul Akmar Mustafa

Abstract:

The peak demand forecast is crucial to identify the future generation plant up needed in the long-term capacity planning analysis for Peninsular Malaysia as well as for the transmission and distribution network planning activities. Currently, peak demand forecast (in Mega Watt) is derived from the generation forecast by using load factor assumption. However, a forecast using this method has underperformed due to the structural changes in the economy, emerging trends and weather uncertainty. The dynamic changes of these drivers will result in many possible outcomes of peak demand for Peninsular Malaysia. This paper will look into the independent model of peak demand forecasting. The model begins with the selection of driver variables to capture long-term growth. This selection and construction of variables, which include econometric, emerging trend and energy variables, will have an impact on the peak forecast. The actual framework begins with the development of system energy and load shape forecast by using the system’s hourly data. The shape forecast represents the system shape assuming all embedded technology and use patterns to continue in the future. This is necessary to identify the movements in the peak hour or changes in the system load factor. The next step would be developing the peak forecast, which involves an iterative process to explore model structures and variables. The final step is combining the system energy, shape, and peak forecasts into the hourly system forecast then modifying it with the forecast adjustments. Forecast adjustments are among other sales forecasts for electric vehicles, solar and other adjustments. The framework will result in an hourly forecast that captures growth, peak usage and new technologies. The advantage of this approach as compared to the current methodology is that the peaks capture new technology impacts that change the load shape.

Keywords: hourly load profile, load forecasting, long term peak demand forecasting, peak demand

Procedia PDF Downloads 173