Assoc. Prof. Naragain Phumchusri, Ph.D.
- 5th Floor of Engineering 4 Bldg., Room 504
- +66-2218-6822
- naragain.p@chula.ac.th
Overview
Dr. Naragain Phumchusri is an associate professor at the Department of Industrial Engineering, Chulalongkorn University, Thailand. She received her Ph.D. in Industrial Engineering from Georgia Institute of Technology, Atlanta, GA, USA in 2010. Her current research interests include stochastic models for revenue management, machine learning for demand forecasting, inventory optimization, warehouse & supply chain management, data analysis for tourism industry and promotion optimization in retails.
Education
Ph.D. in Industrial Engineering
Georgia Institute of Technology, United States, 2010
Master of Science in Industrial Engineering
Georgia Institute of Technology, United States, 2006
B.Eng. in Industrial Engineering
Chulalongkorn University, Thailand, 2004
Expertise
Statistics & Data Analysis
Publications
2021
Chia Ken Tsai, Naragain Phumchusri
Fuzzy analytical hierarchy process for supplier selection: A case study in an electronic component manufacturer Journal Article
In: Engineering Journal, vol. 25, no. 8, pp. 73 – 86, 2021, (Cited by: 20; All Open Access, Gold Open Access, Green Open Access).
@article{Tsai202173,
title = {Fuzzy analytical hierarchy process for supplier selection: A case study in an electronic component manufacturer},
author = {Chia Ken Tsai and Naragain Phumchusri},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85114512893&doi=10.4186%2fej.2021.25.8.73&partnerID=40&md5=441fa64dfcff96d3d36dd47fd1591222},
doi = {10.4186/ej.2021.25.8.73},
year = {2021},
date = {2021-01-01},
journal = {Engineering Journal},
volume = {25},
number = {8},
pages = {73 – 86},
publisher = {Chulalongkorn University, Faculty of Fine and Applied Arts},
abstract = {Supplier selection has become one of the essential effects on the entire electronic supply chain network to gain competitiveness. In the upstream supply chain, companies are able to achieve a high quality and value of products to reduce the potential risks from both internal and external stakeholders by selecting the right suppliers. The case study company produces a nano sim-card connector in which four different types of raw materials are processed into different parts. Currently, the case study company selects each raw material supplier based on its appraisal record. Nevertheless, the appraisal record is measured by the department of procurement. When candidate suppliers are categorized at the same level, the cost becomes the priority criteria to select the supplier, which increases the potential risks of, for example, the components defect rate, a penalty from clients, and a reduction in orders. This paper proposed a Fuzzy analytic hierarchy process (FAHP) model for the selection of raw material suppliers by collecting data from two of the company’s departments (procurement and engineering) and the clients to address qualitative and quantitative elements, uncertainty, and linguistic vagueness based on the company’s scenario in two parts. First, the main and sub-criteria can be weighted using a decision-maker (DM) to identify the level of importance. Second, the FAHP model also dealt with personal preferences and judgement so that the right supplier(s) for each raw material could be selected by collecting and computing the data from the respondents. Then, the sensitivity analysis is applied to observe how the decisions change when the model parameters in the top five sub-criteria change. The proposed model can offer better information and solutions for the DM in the case study company to differentiate the crucial main and sub-criteria and select the suitable raw material suppliers effectively. © 2021, Chulalongkorn University, Faculty of Fine and Applied Arts. All rights reserved.},
note = {Cited by: 20; All Open Access, Gold Open Access, Green Open Access},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Supplier selection has become one of the essential effects on the entire electronic supply chain network to gain competitiveness. In the upstream supply chain, companies are able to achieve a high quality and value of products to reduce the potential risks from both internal and external stakeholders by selecting the right suppliers. The case study company produces a nano sim-card connector in which four different types of raw materials are processed into different parts. Currently, the case study company selects each raw material supplier based on its appraisal record. Nevertheless, the appraisal record is measured by the department of procurement. When candidate suppliers are categorized at the same level, the cost becomes the priority criteria to select the supplier, which increases the potential risks of, for example, the components defect rate, a penalty from clients, and a reduction in orders. This paper proposed a Fuzzy analytic hierarchy process (FAHP) model for the selection of raw material suppliers by collecting data from two of the company’s departments (procurement and engineering) and the clients to address qualitative and quantitative elements, uncertainty, and linguistic vagueness based on the company’s scenario in two parts. First, the main and sub-criteria can be weighted using a decision-maker (DM) to identify the level of importance. Second, the FAHP model also dealt with personal preferences and judgement so that the right supplier(s) for each raw material could be selected by collecting and computing the data from the respondents. Then, the sensitivity analysis is applied to observe how the decisions change when the model parameters in the top five sub-criteria change. The proposed model can offer better information and solutions for the DM in the case study company to differentiate the crucial main and sub-criteria and select the suitable raw material suppliers effectively. © 2021, Chulalongkorn University, Faculty of Fine and Applied Arts. All rights reserved.
2020
Pornpawit Niamjoy, Naragain Phumchusri
Institute of Electrical and Electronics Engineers Inc., 2020, (Cited by: 1).
@conference{Niamjoy20201044,
title = {Forecasting Inbound Tour Daily Demand with Multi Seasonality Pattern: A Case Study of a Tour Operator in Thailand},
author = {Pornpawit Niamjoy and Naragain Phumchusri},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086078936&doi=10.1109%2fICIEA49774.2020.9101918&partnerID=40&md5=310674b00496dedc9ee45fbe0c2e2ecd},
doi = {10.1109/ICIEA49774.2020.9101918},
year = {2020},
date = {2020-01-01},
journal = {2020 IEEE 7th International Conference on Industrial Engineering and Applications, ICIEA 2020},
pages = {1044 – 1048},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Tour operators is playing an important role in Tourism industry which is the essential part of industries for Thai economy. Accurate tourist forecasting is very important input for resource planning (e.g., tour guides, vehicle, etc.) for Tour operators. This paper proposes and compares time-series models to forecast daily demand (number of tourists) for a case study tour operator using the Seasonal Autoregressive Integrated Moving Average model (SARIMA), Seasonal Autoregressive Integrated Moving Average model with exogenous variables model (SARIMAX) and Trigonometric ARMA errors, trend and multiple seasonal patterns (TBATS). The performances are evaluated in terms of Mean Absolute Error (MAE) and Mean Absolute Scaled Error (MASE). The results show that TBATS is the overall most accurate model to forecast the number of tourists using this tour operator's services. Comparing with the same day last year method (the present method which is the case-study company's existing model), TBATS can reduce errors by 48.9% for tour A, 30.6% for tour B and 15.8% for tour C, respectively. © 2020 IEEE.},
note = {Cited by: 1},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Tour operators is playing an important role in Tourism industry which is the essential part of industries for Thai economy. Accurate tourist forecasting is very important input for resource planning (e.g., tour guides, vehicle, etc.) for Tour operators. This paper proposes and compares time-series models to forecast daily demand (number of tourists) for a case study tour operator using the Seasonal Autoregressive Integrated Moving Average model (SARIMA), Seasonal Autoregressive Integrated Moving Average model with exogenous variables model (SARIMAX) and Trigonometric ARMA errors, trend and multiple seasonal patterns (TBATS). The performances are evaluated in terms of Mean Absolute Error (MAE) and Mean Absolute Scaled Error (MASE). The results show that TBATS is the overall most accurate model to forecast the number of tourists using this tour operator’s services. Comparing with the same day last year method (the present method which is the case-study company’s existing model), TBATS can reduce errors by 48.9% for tour A, 30.6% for tour B and 15.8% for tour C, respectively. © 2020 IEEE.
Naragain Phumchusri, Phoom Ungtrakul
Hotel daily demand forecasting for high-frequency and complex seasonality data: a case study in Thailand Journal Article
In: Journal of Revenue and Pricing Management, vol. 19, no. 1, pp. 8 – 25, 2020, (Cited by: 16).
@article{Phumchusri20208,
title = {Hotel daily demand forecasting for high-frequency and complex seasonality data: a case study in Thailand},
author = {Naragain Phumchusri and Phoom Ungtrakul},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85075910899&doi=10.1057%2fs41272-019-00221-6&partnerID=40&md5=f1aa29cf520ceac2b03176e4fbf8b512},
doi = {10.1057/s41272-019-00221-6},
year = {2020},
date = {2020-01-01},
journal = {Journal of Revenue and Pricing Management},
volume = {19},
number = {1},
pages = {8 – 25},
publisher = {Palgrave Macmillan Ltd.},
abstract = {Accurate hotel daily demand forecasting is an important input for hotel revenue management. This research presents forecasting models, both time series and causal methods, for a case study 4-star hotel in Phuket, Thailand. Holt–Winters, Box–Jenkins, Box–Cox transformation, ARMA errors, trend and multiple seasonal patterns (BATS), trigonometric BATS (TBATS), artificial neural network (ANN), and support vector regression are explored. For causal method, independent variables used as regressor inputs are transformed data observed in the past periods, the number of tourist arrivals from main countries to Phuket, Oil prices, exchange rate, etc. Model accuracy is measured using mean absolute percentage error (MAPE) and mean absolute error. Findings suggested that ANN outperforms other models with the lowest MAPE of 8.96%. It shows that Machine Learning techniques studied in this research outperform the advanced time series methods designed for complex seasonality data like BATS and TBATS. Unlike previous works, this research is a pioneer to introduce data transformation as inputs for machine learning models and to compare time series method and machine learning method for hotel daily demand forecasting. The results obtained can be applied to the case study hotel’s future planning about the forecasted number of left-over rooms so that they effectively allocate to their discounted online travel agent more effectively. © 2019, Springer Nature Limited.},
note = {Cited by: 16},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Accurate hotel daily demand forecasting is an important input for hotel revenue management. This research presents forecasting models, both time series and causal methods, for a case study 4-star hotel in Phuket, Thailand. Holt–Winters, Box–Jenkins, Box–Cox transformation, ARMA errors, trend and multiple seasonal patterns (BATS), trigonometric BATS (TBATS), artificial neural network (ANN), and support vector regression are explored. For causal method, independent variables used as regressor inputs are transformed data observed in the past periods, the number of tourist arrivals from main countries to Phuket, Oil prices, exchange rate, etc. Model accuracy is measured using mean absolute percentage error (MAPE) and mean absolute error. Findings suggested that ANN outperforms other models with the lowest MAPE of 8.96%. It shows that Machine Learning techniques studied in this research outperform the advanced time series methods designed for complex seasonality data like BATS and TBATS. Unlike previous works, this research is a pioneer to introduce data transformation as inputs for machine learning models and to compare time series method and machine learning method for hotel daily demand forecasting. The results obtained can be applied to the case study hotel’s future planning about the forecasted number of left-over rooms so that they effectively allocate to their discounted online travel agent more effectively. © 2019, Springer Nature Limited.
Naragain Phumchusri, Phatsakorn Sangsukiam, Nannapat Chariyasethapong
Optimal overbooking model for car rental business with two levels of prices having stochastic joint booking and show-up levels Journal Article
In: Journal of Revenue and Pricing Management, vol. 19, no. 3, pp. 190 – 209, 2020, (Cited by: 2).
@article{Phumchusri2020190,
title = {Optimal overbooking model for car rental business with two levels of prices having stochastic joint booking and show-up levels},
author = {Naragain Phumchusri and Phatsakorn Sangsukiam and Nannapat Chariyasethapong},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85074494250&doi=10.1057%2fs41272-019-00210-9&partnerID=40&md5=023f3d7ce1ecaaab244f365ca102e49a},
doi = {10.1057/s41272-019-00210-9},
year = {2020},
date = {2020-01-01},
journal = {Journal of Revenue and Pricing Management},
volume = {19},
number = {3},
pages = {190 – 209},
publisher = {Palgrave Macmillan Ltd.},
abstract = {Overbooking is a technique in revenue management which offers products or services more than the amount available because there is a possibility that some purchasers may later cancel their purchases. In car rental overbooking problem, overbooking model is complicated because in car rental business, different types of car must be taken into account. This paper presents a mathematical overbooking model for car rental business with two levels of prices in order to find the optimal overbooking levels which minimize the total cost, consisting of opportunity cost, outsourcing cost, and upgrading cost. Booking requests and show-up customers are joint random variables which follow some known joint distributions. Sensitivity analysis is performed to examine the effects of parameters in the overbooking model on the optimal overbooking levels. Due to the complication of the overbooking model, several simplified models are presented as alternative methods for estimating the solutions of the overbooking problem. The results show that the total cost difference between the optimal model and the proposed regression models is in the range of about 3.2–14.09%. The expected total cost when the overbooking policy is implemented is also compared to the total cost when there is no overbooking policy to explore how overbooking decision is significant in minimizing total cost. © 2019, Springer Nature Limited.},
note = {Cited by: 2},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Overbooking is a technique in revenue management which offers products or services more than the amount available because there is a possibility that some purchasers may later cancel their purchases. In car rental overbooking problem, overbooking model is complicated because in car rental business, different types of car must be taken into account. This paper presents a mathematical overbooking model for car rental business with two levels of prices in order to find the optimal overbooking levels which minimize the total cost, consisting of opportunity cost, outsourcing cost, and upgrading cost. Booking requests and show-up customers are joint random variables which follow some known joint distributions. Sensitivity analysis is performed to examine the effects of parameters in the overbooking model on the optimal overbooking levels. Due to the complication of the overbooking model, several simplified models are presented as alternative methods for estimating the solutions of the overbooking problem. The results show that the total cost difference between the optimal model and the proposed regression models is in the range of about 3.2–14.09%. The expected total cost when the overbooking policy is implemented is also compared to the total cost when there is no overbooking policy to explore how overbooking decision is significant in minimizing total cost. © 2019, Springer Nature Limited.
Ontheera Hwandee, Naragain Phumchusri
Forecasting International Tourist Arrivals from Major Countries to Thailand Journal Article
In: Lecture Notes in Electrical Engineering, vol. 619, pp. 115 – 125, 2020, (Cited by: 4).
@article{Hwandee2020115,
title = {Forecasting International Tourist Arrivals from Major Countries to Thailand},
author = {Ontheera Hwandee and Naragain Phumchusri},
editor = {Zakaria Z. and Ahmad R.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85077501012&doi=10.1007%2f978-981-15-1289-6_11&partnerID=40&md5=3133e7c2e1e1a295f3246c5c3d767800},
doi = {10.1007/978-981-15-1289-6_11},
year = {2020},
date = {2020-01-01},
journal = {Lecture Notes in Electrical Engineering},
volume = {619},
pages = {115 – 125},
publisher = {Springer},
abstract = {Tourism industry is one of the most important industries for Thai economy. This paper proposes and compares forecasting models for international tourism arrivals to Thailand. Since country-specific forecasting models can reflect the uniqueness of each country of origin, major countries for Thai tourism, namely China, Malaysia, Korea, Japan, and Russia are explored. The data used in this research is the number of international tourist arrivals from those countries recorded monthly from Jan 2013 to Sep 2018. The performance of the Seasonal Autoregressive Integrated Moving Average model (SARIMA) and the multiple regression model are evaluated in terms of Mean Absolute Percentage Error (MAPE). Several important economic factors such as income, price, exchange rate, and qualitative factors, represented by dummy variables of seasonal effect are explored to understand their effects on international tourism demand. The results show that the SARIMA is preferred to forecast international tourism arrivals from Malaysia, while multiple regression provides lowest errors for other interested countries. © 2020, Springer Nature Singapore Pte Ltd.},
note = {Cited by: 4},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Tourism industry is one of the most important industries for Thai economy. This paper proposes and compares forecasting models for international tourism arrivals to Thailand. Since country-specific forecasting models can reflect the uniqueness of each country of origin, major countries for Thai tourism, namely China, Malaysia, Korea, Japan, and Russia are explored. The data used in this research is the number of international tourist arrivals from those countries recorded monthly from Jan 2013 to Sep 2018. The performance of the Seasonal Autoregressive Integrated Moving Average model (SARIMA) and the multiple regression model are evaluated in terms of Mean Absolute Percentage Error (MAPE). Several important economic factors such as income, price, exchange rate, and qualitative factors, represented by dummy variables of seasonal effect are explored to understand their effects on international tourism demand. The results show that the SARIMA is preferred to forecast international tourism arrivals from Malaysia, while multiple regression provides lowest errors for other interested countries. © 2020, Springer Nature Singapore Pte Ltd.
Jiaranai Awichanirost, Naragain Phumchusri
Institute of Electrical and Electronics Engineers Inc., 2020, (Cited by: 4).
@conference{Awichanirost20201014,
title = {Analyzing the Effects of Sessions on Unique Visitors and Unique Page Views with Google Analytics: A case study of a Tourism Website in Thailand},
author = {Jiaranai Awichanirost and Naragain Phumchusri},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086075434&doi=10.1109%2fICIEA49774.2020.9102094&partnerID=40&md5=9258acbe6544c9ea131e200c08ed7a49},
doi = {10.1109/ICIEA49774.2020.9102094},
year = {2020},
date = {2020-01-01},
journal = {2020 IEEE 7th International Conference on Industrial Engineering and Applications, ICIEA 2020},
pages = {1014 – 1018},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The tourism industry plays an important role in Thailand's GDP which has given a huge economic boost every year. As we know, most of the tour operators own websites that are accessible worldwide and usually measured by the performance of online marketing. Therefore, the purpose of this paper is to develop a methodology to analyze the effects of sessions on unique visitors and unique page views of tourism websites based on time series data on Google analytics. This cannot be defined by simple regression as it depends on multiple factors, i.e., visitor types, traffic(channels) and technology (browsers). Besides, this paper describes how to use the most accurate data to gain an effective result. The results can be applied to other tourism websites for their analysis as well. © 2020 IEEE.},
note = {Cited by: 4},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
The tourism industry plays an important role in Thailand’s GDP which has given a huge economic boost every year. As we know, most of the tour operators own websites that are accessible worldwide and usually measured by the performance of online marketing. Therefore, the purpose of this paper is to develop a methodology to analyze the effects of sessions on unique visitors and unique page views of tourism websites based on time series data on Google analytics. This cannot be defined by simple regression as it depends on multiple factors, i.e., visitor types, traffic(channels) and technology (browsers). Besides, this paper describes how to use the most accurate data to gain an effective result. The results can be applied to other tourism websites for their analysis as well. © 2020 IEEE.
Phongsatorn Amornvetchayakul, Naragain Phumchusri
Institute of Electrical and Electronics Engineers Inc., 2020, (Cited by: 8).
@conference{Amornvetchayakul2020514,
title = {Customer Churn Prediction for a Software-as-a-Service Inventory Management Software Company: A Case Study in Thailand},
author = {Phongsatorn Amornvetchayakul and Naragain Phumchusri},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086066217&doi=10.1109%2fICIEA49774.2020.9102099&partnerID=40&md5=006a9bd7f741ce2288a5a402adeae5aa},
doi = {10.1109/ICIEA49774.2020.9102099},
year = {2020},
date = {2020-01-01},
journal = {2020 IEEE 7th International Conference on Industrial Engineering and Applications, ICIEA 2020},
pages = {514 – 518},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Software-as-a-Service is the fast growth and high market values as a new emerging online business. Customer churn is a critical measure for this business. Thus, this paper focuses on seeking a customer churn prediction model for a Software-as-a-Service inventory management software company in Thailand which is facing a high churn rate. This paper executes the prediction models with four machine learning algorithms: logistic regression, support vector machine, decision tree and random forest. The random forest model is capable to provide lowest error with 10-fold cross validation average scores of 91.6% recall and 92.6% F1-score. Moreover, feature importance scores can highlight useful insights of case-study that business metrics are significantly related to churn behavior. As a result, this paper is beneficial to the case-study company to help indicate real churn customer and enhance the effectiveness in executive decision and marketing campaign. © 2020 IEEE.},
note = {Cited by: 8},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Software-as-a-Service is the fast growth and high market values as a new emerging online business. Customer churn is a critical measure for this business. Thus, this paper focuses on seeking a customer churn prediction model for a Software-as-a-Service inventory management software company in Thailand which is facing a high churn rate. This paper executes the prediction models with four machine learning algorithms: logistic regression, support vector machine, decision tree and random forest. The random forest model is capable to provide lowest error with 10-fold cross validation average scores of 91.6% recall and 92.6% F1-score. Moreover, feature importance scores can highlight useful insights of case-study that business metrics are significantly related to churn behavior. As a result, this paper is beneficial to the case-study company to help indicate real churn customer and enhance the effectiveness in executive decision and marketing campaign. © 2020 IEEE.
Ronnachai Jirapongpan, Naragain Phumchusri
Prediction of the Profitability of Pairs Trading Strategy Using Machine Learning Conference
Institute of Electrical and Electronics Engineers Inc., 2020, (Cited by: 7).
@conference{Jirapongpan20201025,
title = {Prediction of the Profitability of Pairs Trading Strategy Using Machine Learning},
author = {Ronnachai Jirapongpan and Naragain Phumchusri},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086070407&doi=10.1109%2fICIEA49774.2020.9102013&partnerID=40&md5=8e525d30ab0cee7729ab71790e9728de},
doi = {10.1109/ICIEA49774.2020.9102013},
year = {2020},
date = {2020-01-01},
journal = {2020 IEEE 7th International Conference on Industrial Engineering and Applications, ICIEA 2020},
pages = {1025 – 1030},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Pairs trading strategy is one of the well-known quantitative trading strategy developed in 1980s by the team of scientists. There are many researchers trying to study and create the mathematical model to improve the pairs trading strategy on various assets such as cointegration method, OLS, Kalmann filter, Machine learning, etc. The purpose of the models is to generate the precise signals from pairs of assets to maximize the return based on statistical arbitrage of pairs trading strategy. In this paper, Stress Indicator pairs trading strategy is studied further. Stress Indicator pairs trading strategy is easy, straightforward and profitable. However, There are many factors which influence the profitability of the strategy, causing the loss trades. We purpose a novel approach by using the machine learning algorithm to learn the historical trades of Stress Indicator pairs trading strategy in foreign exchage rates and to predict the profitability in the future trades. The pairs of the exchange rate are filtered by choosing only the pairs which generate the positive average return per trade from Stress Indicator pairs trading strategy in the past. The capability of the ML models is to classify whether the signals from Stress Indicator pairs trading strategy is profitable or not before opening the positions. The powerful ML models, Artificial Neural network and XGBoost, are implemented in this study. Several factors which could influence the profitability such as correlation, volatility OLS beta are collected and used to train the model following the common step of ML training procedures such as features selection, Hyperparameter tuning and k-Fold cross validation to generate the capable models. Next, the performance of ANN and XGBoost is compared that which one performs better by the score matrix. The result shows that the performance of predicting the profitability is not significantly different. Both models mostly achieve 60% accuracy in In-sample data, but the accuracy in out-of-sample data is quite fluctuated. In other words, ML models are capable to classify the profitable signal from price behavior but may lack of consistency. © 2020 IEEE.},
note = {Cited by: 7},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Pairs trading strategy is one of the well-known quantitative trading strategy developed in 1980s by the team of scientists. There are many researchers trying to study and create the mathematical model to improve the pairs trading strategy on various assets such as cointegration method, OLS, Kalmann filter, Machine learning, etc. The purpose of the models is to generate the precise signals from pairs of assets to maximize the return based on statistical arbitrage of pairs trading strategy. In this paper, Stress Indicator pairs trading strategy is studied further. Stress Indicator pairs trading strategy is easy, straightforward and profitable. However, There are many factors which influence the profitability of the strategy, causing the loss trades. We purpose a novel approach by using the machine learning algorithm to learn the historical trades of Stress Indicator pairs trading strategy in foreign exchage rates and to predict the profitability in the future trades. The pairs of the exchange rate are filtered by choosing only the pairs which generate the positive average return per trade from Stress Indicator pairs trading strategy in the past. The capability of the ML models is to classify whether the signals from Stress Indicator pairs trading strategy is profitable or not before opening the positions. The powerful ML models, Artificial Neural network and XGBoost, are implemented in this study. Several factors which could influence the profitability such as correlation, volatility OLS beta are collected and used to train the model following the common step of ML training procedures such as features selection, Hyperparameter tuning and k-Fold cross validation to generate the capable models. Next, the performance of ANN and XGBoost is compared that which one performs better by the score matrix. The result shows that the performance of predicting the profitability is not significantly different. Both models mostly achieve 60% accuracy in In-sample data, but the accuracy in out-of-sample data is quite fluctuated. In other words, ML models are capable to classify the profitable signal from price behavior but may lack of consistency. © 2020 IEEE.
Naina Chugh, Naragain Phumchusri
Bangkok Tours and Activities Data Analysis via User-Generated Content Conference
Institute of Electrical and Electronics Engineers Inc., 2020, (Cited by: 3).
@conference{Chugh202098,
title = {Bangkok Tours and Activities Data Analysis via User-Generated Content},
author = {Naina Chugh and Naragain Phumchusri},
editor = {Miraz M.H. and Excell P.S. and Ware A. and Soomro S. and Ali M.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85096978650&doi=10.1109%2fiCCECE49321.2020.9231211&partnerID=40&md5=ace7ecd3f38199a72165e5cd11dec4c8},
doi = {10.1109/iCCECE49321.2020.9231211},
year = {2020},
date = {2020-01-01},
journal = {Proceedings - 2020 International Conference on Computing, Electronics and Communications Engineering, iCCECE 2020},
pages = {98 – 102},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The overarching goal of this paper is to gain visibility on tourist preferences and whether or not the needs of tourists are being met. With the Travel and Tourism (TT) sector being the backbone to the global economy and the sector becoming more saturated and competitive, insights on TT are vital now, more than ever. The rise of social media and user-generated content has effectuated the opportunity for a systematic analysis of tourist preferences via user-generated content. This paper is focused on gaining insights of tourism in Bangkok, Thailand through user-generated content scraped from TripAdvisor's online reviews of tours and activities. In order to develop insights on tourist preferences and tourism trends in Bangkok, various analyses were implemented, including sentiment analysis to gather tourist point-of-view, association rules mining to find patterns of preferences, and natural language processing along with text frequency analysis to understand what features tourists are most frequently talking about. This paper also developed prediction models using logistic regression to forecast 5-start ratings and 1-star ratings of reviews-with the purpose of identifying factors that significantly affect position and negative sentiments on tours/activities. © 2020 IEEE.},
note = {Cited by: 3},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
The overarching goal of this paper is to gain visibility on tourist preferences and whether or not the needs of tourists are being met. With the Travel and Tourism (TT) sector being the backbone to the global economy and the sector becoming more saturated and competitive, insights on TT are vital now, more than ever. The rise of social media and user-generated content has effectuated the opportunity for a systematic analysis of tourist preferences via user-generated content. This paper is focused on gaining insights of tourism in Bangkok, Thailand through user-generated content scraped from TripAdvisor’s online reviews of tours and activities. In order to develop insights on tourist preferences and tourism trends in Bangkok, various analyses were implemented, including sentiment analysis to gather tourist point-of-view, association rules mining to find patterns of preferences, and natural language processing along with text frequency analysis to understand what features tourists are most frequently talking about. This paper also developed prediction models using logistic regression to forecast 5-start ratings and 1-star ratings of reviews-with the purpose of identifying factors that significantly affect position and negative sentiments on tours/activities. © 2020 IEEE.
2019
Naragain Phumchusri, Supasit Tangsiriwattana
Optimal supplier selection model with multiple criteria: A case study in the automotive parts industry Journal Article
In: Engineering Journal, vol. 23, no. 1, pp. 191 – 203, 2019, (Cited by: 12; All Open Access, Gold Open Access, Green Open Access).
@article{Phumchusri2019191,
title = {Optimal supplier selection model with multiple criteria: A case study in the automotive parts industry},
author = {Naragain Phumchusri and Supasit Tangsiriwattana},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85066987081&doi=10.4186%2fej.2019.23.1.191&partnerID=40&md5=7e8661d053d830692e7802265499e42f},
doi = {10.4186/ej.2019.23.1.191},
year = {2019},
date = {2019-01-01},
journal = {Engineering Journal},
volume = {23},
number = {1},
pages = {191 – 203},
publisher = {Chulalongkorn University},
abstract = {This research proposes a mathematical model for supplier selection for a case-study car seat manufacturer. This research is divided into 2 parts. The first part is the raw material supplier evaluation method using Analytic Hierarchy Process. This part weights the importance of main decision criteria and sub-decision criteria, complying with part makers' satisfaction. The result from the first part is scores for each raw material supplier resulting from multiple evaluation criteria. The second part proposes a mathematical model for supplier selection using integer programming. The scores of each supplier from the first part will be considered along with raw material consumption to select the suitable raw material suppliers that maximize overall part makers' satisfaction. The results from the first part of this research show that the most important criterion for supplier evaluation is cost, which is about 41%. Quality, Delivery, Service, and Risk factors are approximately 24%, 14%, 12% and 9%, respectively. The result from the second part shows that the model can effectively match material suppliers to part makers according to their preferences. Comparing with current situation, the satisfaction is increased by 26% with this proposed framework. It means the proposed model can help matching the right supplier to each part maker that can increase overall satisfactions for this case-study's supply chain. © 2019, Chulalongkorn University. All rights reserved.},
note = {Cited by: 12; All Open Access, Gold Open Access, Green Open Access},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This research proposes a mathematical model for supplier selection for a case-study car seat manufacturer. This research is divided into 2 parts. The first part is the raw material supplier evaluation method using Analytic Hierarchy Process. This part weights the importance of main decision criteria and sub-decision criteria, complying with part makers’ satisfaction. The result from the first part is scores for each raw material supplier resulting from multiple evaluation criteria. The second part proposes a mathematical model for supplier selection using integer programming. The scores of each supplier from the first part will be considered along with raw material consumption to select the suitable raw material suppliers that maximize overall part makers’ satisfaction. The results from the first part of this research show that the most important criterion for supplier evaluation is cost, which is about 41%. Quality, Delivery, Service, and Risk factors are approximately 24%, 14%, 12% and 9%, respectively. The result from the second part shows that the model can effectively match material suppliers to part makers according to their preferences. Comparing with current situation, the satisfaction is increased by 26% with this proposed framework. It means the proposed model can help matching the right supplier to each part maker that can increase overall satisfactions for this case-study’s supply chain. © 2019, Chulalongkorn University. All rights reserved.