Business Intelligence in Airline Passenger Satisfaction Study—A Fuzzy-Genetic Approach with Optimized Interpretability-Accuracy Trade-Off
Abstract
:1. Introduction
2. Kaggle’s Airline Passenger Satisfaction Data
3. Methodology: An Outline of Main Components of the Proposed FRBCs and Their MOEOA-Based Learning and Optimization
- (a)
- in our original approach implemented in SPEA3, the complementary operations of increasing and reducing the archive lead to obtaining the best available distribution balance and spread of solutions belonging to Pareto-front approximation (see [19] for a detailed presentation and [20] for a discussion), whereas
- (b)
- in SPEA2 only the truncation procedure (if activated) contributes to improving the distribution balance and diversity of the final set of solutions (not addressing, however, the problem of improving the spread of solutions) and giving, in general, worse results than its counterpart of SPEA3.
4. Experiments (Application to Kaggle’s Airline Passenger Satisfaction Data) and Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Grossmann, W.; Rinderle-Ma, S. Fundamentals of Business Intelligence; Springer: Berlin/Heidelberg, Germany, 2015. [Google Scholar]
- Luhn, H.P. A Business Intelligence System. IBM J. Res. Dev. 1958, 2, 314–319. [Google Scholar] [CrossRef]
- Sharda, R.; Turban, E.; Delen, D.; Aronson, J.; Liang, T. Business Intelligence and Analytics: Systems for Decision Support; Always Learning; Pearson: London, UK, 2014. [Google Scholar]
- Akerkar, R.; Sajja, P. Knowledge-Based Systems, 1st ed.; Jones and Bartlett Publishers, Inc.: Burlington, MA, USA, 2009. [Google Scholar]
- Kumar, S.; Zymbler, M. A machine learning approach to analyze customer satisfaction from airline tweets. J. Big Data 2019, 6. [Google Scholar] [CrossRef] [Green Version]
- Bogicevic, V.; Yang, W.; Bujisic, M.; Bilgihan, A. Visual Data Mining: Analysis of Airline Service Quality Attributes. J. Qual. Assur. Hosp. Tour. 2017, 18, 1–22. [Google Scholar] [CrossRef]
- Ban, H.J.; Kim, H.S. Understanding Customer Experience and Satisfaction through Airline Passengers’ Online Review. Sustainability 2019, 11, 4066. [Google Scholar] [CrossRef] [Green Version]
- Yakut, I.; Turkoglu, T.; Yakut, F. Understanding Customer’s Evaluations Through Mining Airline Reviews. Int. J. Data Min. Knowl. Manag. Process 2015, 5, 1–11. [Google Scholar] [CrossRef]
- Tsafarakis, S.; Kokotas, T.; Pantouvakis, A. A multiple criteria approach for airline passenger satisfaction measurement and service quality improvement. J. Air Transp. Manag. 2018, 68, 61–75. [Google Scholar] [CrossRef]
- Zhang, P.; Fan, C.; Xu, Q.; Ran, X.; Yu, L.; Fang, D.; Zhang, Z. Applications of Business Intelligence Technology in the Airports and Airlines Companies. Int. J. Appl. Sci. Technol. 2011, 1, 74–78. [Google Scholar]
- Rudziński, F. A multi-objective genetic optimization of interpretability-oriented fuzzy rule-based classifiers. Appl. Soft Comput. 2016, 38, 118–133. [Google Scholar] [CrossRef]
- Gorzałczany, M.B.; Rudziński, F. A multi-objective genetic optimization for fast, fuzzy rule-based credit classification with balanced accuracy and interpretability. Appl. Soft Comput. 2016, 40, 206–220. [Google Scholar] [CrossRef]
- Gorzałczany, M.B.; Rudziński, F. Interpretable and accurate medical data classification-a multi-objective genetic-fuzzy optimization approach. Expert Syst. Appl. 2017, 71, 26–39. [Google Scholar] [CrossRef]
- Gorzałczany, M.B.; Rudziński, F. Handling fuzzy systems’ accuracy-interpretability trade-off by means of multi-objective evolutionary optimization methods-selected problems. Bull. Pol. Acad. Sci. Tech. Sci. 2015, 63, 791–798. [Google Scholar] [CrossRef] [Green Version]
- Li, W.; Yu, S.; Pei, H.; Zhao, C.; Tian, B. A hybrid approach based on fuzzy AHP and 2-tuple fuzzy linguistic method for evaluation in-flight service quality. J. Air Transp. Manag. 2017, 60, 49–64. [Google Scholar] [CrossRef]
- Fazzolari, M.; Alcala, R.; Nojima, Y.; Ishibuchi, H.; Herrera, F. A review of the application of multiobjective evolutionary fuzzy systems: Current status and further directions. IEEE Trans. Fuzzy Syst. 2013, 21, 45–65. [Google Scholar] [CrossRef]
- Gorzałczany, M.B.; Rudziński, F. Accuracy vs. interpretability of fuzzy rule-based classifiers-an evolutionary approach. In Artificial Intelligence and Soft Computing-ICAISC 2012; Lecture Notes in Computer Science; Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Żurada, J.M., Eds.; Springer: Berlin/Heidelberg, Germany, 2012; Volume 7269, pp. 222–230. [Google Scholar]
- Gorzałczany, M.B.; Rudziński, F. A modified Pittsburg approach to design a genetic fuzzy rule-based classifier from data. In Artificial Intelligence and Soft Computing-ICAISC 2010; Lecture Notes in Computer Science; Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Żurada, J.M., Eds.; Springer: Berlin/Heidelberg, Germany, 2010; Volume 6113, pp. 88–96. [Google Scholar]
- Rudziński, F. Finding sets of non-dominated solutions with high spread and well-balanced distribution using generalized strength Pareto evolutionary algorithm. In Advances in Intelligent Systems Research, Proceedings of the 2015 Conference International Fuzzy Systems Association and European Society for Fuzzy Logic and Technology (IFSA-EUSFLAT-15); Alonso, J.M., Bustince, H., Reformat, M., Eds.; Atlantis Press: Gijón, Spain, 2015; Volume 89, pp. 178–185. [Google Scholar]
- Gorzałczany, M.B.; Rudziński, F. An improved multi-objective evolutionary optimization of data-mining-based fuzzy decision support systems. In Proceedings of the 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Vancouver, BC, Canada, 25–29 July 2016; pp. 2227–2234. [Google Scholar]
- Gorzałczany, M.B.; Rudziński, F. A multi-objective-genetic-optimization-based data-driven fuzzy classifier for technical applications. In Proceedings of the 2016 IEEE 25th International Symposium on Industrial Electronics (ISIE), Santa Clara, CA, USA, 8–10 June 2016; pp. 78–83. [Google Scholar]
- Zitzler, E.; Laumanns, M.; Thiele, L. SPEA2: Improving the strength Pareto evolutionary algorithm for multi-objective optimization. In Proceedings of the Evol. Methods for Design, Optimization and Control with Applications to Industrial Problems, Athens, Greece, 19–21 September 2001; pp. 95–100. [Google Scholar]
- John, D. US Airline Passenger Satisfaction Data Set (Version 2). Available online: https://www.kaggle.com/johndddddd/customer-satisfaction (accessed on 26 December 2020).
- Patlolla, H.R. US Airline Passenger Satisfaction. MWSUG 2019, RF-079, 1–12. [Google Scholar]
- Gacto, M.J.; Alcala, R.; Herrera, F. Interpretability of linguistic fuzzy rule-based systems: An overview of interpretability measures. Inf. Sci. 2011, 181, 4340–4360. [Google Scholar] [CrossRef]
- Deb, K.; Pratap, A.; Agarwal, S.; Meyarivan, T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 2002, 6, 182–197. [Google Scholar] [CrossRef] [Green Version]
- Zhuo, X.; Zhang, J.; Son, S.W. Network intrusion detection using word embeddings. In Proceedings of the 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, USA, 11–14 December 2017; pp. 4686–4695. [Google Scholar]
- J. D. POWER. North America Airline Satisfaction Study. 2021. Available online: https://www.jdpower.com/business/travel-and-hospitality/north-america-airline-satisfaction-study (accessed on 26 December 2020).
- American Customer Satisfaction Index (ACSI). ACSI Travel Report 2020–2021. Available online: https://www.theacsi.org (accessed on 26 December 2020).
- Hayadi, B.H.; Kim, J.M.; Hulliyah, K.; Sukmana, H. Predicting Airline Passenger Satisfaction with Classification Algorithms. Int. J. Inform. Inf. Syst. 2021, 4, 82–94. [Google Scholar]
- Park, S.; Lee, J.S.; Nicolau, J.L. Understanding the dynamics of the quality of airline service attributes: Satisfiers and dissatisfiers. Tour. Manag. 2020, 81, 104163. [Google Scholar] [CrossRef]
- Soomro, D.Y.; Hameed, D.I.; Shakoor, R.; Kaimkhani, S. Factors effecting consumer preferences in airline industry. Far East J. Psychol. Bus. 2012, 7, 63–72. [Google Scholar]
- Abdulsalam, M.A.; Miskeen, B.; Alhodairi, A.M.; Abdullah, R.A.; Ehsan, S. Evaluate the Service Quality of Local Airline Companies in Libya Using Importance-Satisfaction Analysis. Aust. J. Basic Appl. Sci. 2013, 7, 154–165. [Google Scholar]
- Arrieta, A.B.; Diaz-Rodriguez, N.; Del Ser, J.; Bennetot, A.; Tabik, S.; Barbado, A.; Garcia, S.; Gil-Lopez, S.; Molina, D.; Benjamins, R.; et al. Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 2020, 58, 82–115. [Google Scholar] [CrossRef] [Green Version]
- Samek, W.; Montavon, G.; Vedaldi, A.; Hansen, L.; Müller, K.R. (Eds.) Explainable AI: Interpreting, Explaining and Visualizing Deep Learning; Lecture Notes in Artificial Intelligence; Springer Nature Switzerland AG: Cham, Switzerland, 2019. [Google Scholar]
- Monar, C. Interpretable Machine Learning. A Guide for Making Black Box Models Explainable. Published online under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. 2020. pp. 1–318. Available online: https://christophm.github.io/interpretable-ml-book/ (accessed on 26 December 2020).
- Escalante, H.J.; Escalera, S.; Guyon, I.; Baró, X.; Güçlütürk, Y.; Güçlü, U.; Gerven, M. (Eds.) Explainable and Interpretable Models in Computer Vision and Machine Learning; The Springer Series on Challenges in Machine Learning; Springer Nature Switzerland AG: Cham, Switzerland, 2018. [Google Scholar]
No. | Attribute Name | Attribute Type | Attribute Domain Details (·%—Percentage of the Overall Number of Samples) | ||
---|---|---|---|---|---|
1. | id | numerical | Passenger’s id (not used in our experiments) | ||
2. | satisfaction_v2 | class label | 2 class labels: "neutral or dissatisfied" (49%) and "satisfied" (51%) | ||
3. | Gender | nominal | 2 terms: “female” (51%) and “male” (49%) | ||
4. | Customer type | ” | 2 terms: “loyal customer” (82%) and “disloyal customer” (18%) | ||
5. | Age | numerical | integer numbers from 7 to 85 (average: 39.2, std. deviation: 15.1) | ||
6. | Type of travel | nominal | 2 terms: “personal travel” (31%) and “business travel” (69%) | ||
7. | Class | ” | 3 terms: “eco” (46%), “business” (48%), and “eco plus” (7%) | ||
8. | Flight distance | numerical | integer numbers from 31 to 6907 (average: 1590.3, std. deviation: 1082.5) | ||
9. | Inflight WiFi service | ordinal | ‘0’ (1.6%) | ‘1’ (14.3%) | ‘2’ (22.9%) |
‘3’ (23.0%) | ‘4’ (21.7%) | ‘5’ (16.6%) | |||
10. | Departure/Arrival time convenient | ” | ‘0’ (5.1%) | ‘1’ (15.5%) | ‘2’ (17.1%) |
‘3’ (17.5%) | ‘4’ (23.7%) | ‘5’ (21.1%) | |||
11. | Ease of online booking | ” | ‘0’ (2.2%) | ‘1’ (13.6%) | ‘2’ (19.2%) |
’3’ (20.3%) | ‘4’ (24.8%) | ‘5’ (19.8%) | |||
12. | Gate location | ” | ‘0’ (0%) | ‘1’ (17.2%) | ‘2’ (18.8%) |
’3’ (26.7%) | ‘4’ (23.3%) | ‘5’ (14.1%) | |||
13. | Food and drink | ” | ‘0’ (2.3%) | ‘1’ (14.3%) | ‘2’ (21%) |
’3’ (21.5%) | ‘4’ (22.2%) | ‘5’ (18.6%) | |||
14. | Online boarding | ” | ‘0’ (1.2%) | ‘1’ (11%) | ‘2’ (15.6%) |
’3’ (22.3%) | ‘4’ (28.4%) | ‘5’ (21.6%) | |||
15. | Seat comfort | ” | ‘0’ (1.8%) | ‘1’ (13.9%) | ‘2’ (18.2%) |
‘3’ (20.2%) | ‘4’ (26.2%) | ‘5’ (19.6%) | |||
16. | Inflight entertainment | ” | ‘0’ (1.2%) | ‘1’ (10.6%) | ‘2’ (15.8%) |
‘3’ (18.5%) | ‘4’ (30.3%) | ‘5’ (23.6%) | |||
17. | On-board service | ” | ’0’ (0%) | ’1’ (10.8%) | ’2’ (13.7%) |
‘3’ (21.4%) | ‘4’ (30.6%) | ’5’ (23.6%) | |||
18. | Leg room service | ” | ‘0’ (0.4%) | ‘1’ (9.3%) | ’2’ (17.8%) |
’3’ (18.3%) | ‘4’ (29.1%) | ‘5’ (25.1%) | |||
19. | Baggage handling | ” | ‘0’ (0%) | ‘1’ (6.5%) | ‘2’ (10.7%) |
‘3’ (19.4%) | ‘4’ (36.6%) | ‘5’ (26.8%) | |||
20. | Checkin service | ” | ‘0’ (0%) | ‘1’ (12.1%) | ’2’ (12.2%) |
‘3’ (27.3%) | ‘4’ (28%) | ‘5’ (20.4%) | |||
21. | Cleanliness | ” | ‘0’ (0%) | ‘1’ (9.4%) | ‘2’ (12.9%) |
‘3’ (21%) | ‘4’ (31.9%) | ‘5’ (24.8%) | |||
22. | Departure delay in minutes | numerical | integer numbers from 0 to 1592 (average: 14.6, std. deviation: 39.0) | ||
23. | Arrival delay in minutes | ” | integer numbers from 0 to 1584 (average: 14.9, std. deviation: 39.4) |
Environmental Selection Procedure of SPEA2: | Our Original Environmental Selection Procedure Implemented in SPEA3: |
---|---|
(a) immediately (i.e., in each generation of the optimization process) copies to the archive all available non-dominated solutions (if their number is lesser than the archive size, the best dominated solutions from the current population are also selected and copied to the archive to fully fill it), | (a) gradually (i.e., in the subsequent generations of the optimization process) fills the archive with only such non-dominated solutions which ensure the best balance of distances between neighboring solutions in the archive, |
(b) truncates overfilled archive by removing from it redundant solutions characterized by the shortest distances to other solutions. | (b) truncates archive by removing from it solutions which have been dominated by any new solutions that have appeared in the current population, |
(c) gradually exchanges some non-dominated solutions between the archive and the current population in order to maximize the sum of distances between the nearest neighboring solutions in the archive. |
No. | Objective Function Complements | Interpretability Measures | Accuracy Measures | |||||
---|---|---|---|---|---|---|---|---|
1. | 0 | 0.4498 | 3 | 1 | 3 | 1 | 75.1% | 75.2% |
2. | 0.035 | 0.4214 | 5 | 2 | 6 | 1.4 | 77.2% | 77.2% |
3. | 0.0892 | 0.3917 | 7 | 4 | 11 | 1.6 | 80.5% | 80.5% |
4. | 0.1187 | 0.3693 | 8 | 5 | 13 | 1.7 | 82.8% | 82.8% |
5. | 0.1555 | 0.3497 | 9 | 6 | 15 | 2.2 | 84.6% | 84.5% |
6. | 0.2113 | 0.3336 | 11 | 8 | 18 | 2.4 | 86.6% | 86.4% |
7. | 0.2808 | 0.3216 | 17 | 11 | 25 | 2.2 | 88.3% | 88.1% |
8. | 0.3514 | 0.3143 | 17 | 13 | 31 | 3.1 | 88.5% | 88.2% |
9. | 0.4654 | 0.3119 | 21 | 17 | 37 | 3.6 | 88.8% | 88.5% |
10. | 0.5805 | 0.311 | 27 | 21 | 45 | 4.2 | 88.9% | 88.6% |
No. | Fuzzy Classification Rules | |
---|---|---|
Solution No. 1 (, ): | ||
1. | IF | Inflight entertainment is no_answer or low THEN Passenger is neutral or dissatisfied |
2. | IF | Inflight entertainment is medium THEN Passenger is neutral or dissatisfied |
3. | IF | Inflight entertainment is high THEN Passenger is satisfied |
Solution No. 2 (, ): | ||
1. | This rule is an extension of rule No. 1 from Solution No. 1: | |
IF | Inflight entertainment is no_answer or low AND Seat comfort is low or medium THEN Passenger is neutral or dissatisfied | |
2. | This rule is an extension of rule No. 2 from Solution No. 1: | |
IF | Inflight entertainment is medium AND Seat comfort is low or medium THEN Passenger is neutral or dissatisfied | |
3. | This rule is the same as rule No. 3 from Solution No. 1. | |
4. | IF | Seat comfort is no_answer THEN Passenger is satisfied |
5. | IF | Seat comfort is high THEN Passenger is satisfied |
Solution No. 3 (, ): | ||
1. | This rule is the same as rule No. 1 from Solution No. 1. | |
2. | This rule is the same as rule No. 2 from Solution No. 2. | |
3. | This rule is an extension of rule No. 3 from Solution No. 2: | |
IF | Inflight entertainment is high AND Type of travel is business travel THEN Passenger is satisfied | |
4. | This rule is the same as rule No. 4 from Solution No. 2. | |
5. | This rule is an extension of rule No. 5 from Solution No. 2: | |
IF | Seat comfort is high AND Inflight WiFi service is high THEN Passenger is satisfied | |
6. | IF | Inflight WiFi service is low or medium AND Type of travel is personal travel THEN Passenger is neutral or dissatisfied |
7. | IF | Inflight WiFi service is no_answer THEN Passenger is satisfied |
Solution No. 4 (, ): | ||
1–2. | These rules are the same as rules Nos. 1 and 2 from Solution No. 2. | |
3. | This rule is an extension of rule No. 3 from Solution No. 3: | |
IF | Inflight entertainment is high AND Type of travel is business travel AND Customer type is loyal customer THEN Passenger is satisfied | |
4–7. | These rules are the same as rules Nos. 4–7 from Solution No. 3. | |
8. | IF | Customer type is disloyal customer AND Inflight WiFi service is low (or medium) THEN Passenger is neutral or dissatisfied |
Solution No. 5 (, ): | ||
1–4. | These rules are the same as rules Nos. 1–4 from Solution No. 4. | |
5. | This rule is the second extension of rule No. 5 from Solution No. 2: | |
IF | Seat comfort is high AND Flight distance is long THEN Passenger is satisfied | |
6. | This rule is an extension of rule No. 6 from Solution No. 4: | |
IF | Inflight WiFi service is low or medium AND Type of travel is personal travel AND Flight distance is short THEN Passenger is neutral or dissatisfied | |
7. | This rule is the same as rule No. 7 from Solution No. 4. | |
8. | IF | Inflight WiFi service is high AND Flight distance is short THEN Passenger is satisfied |
9. | IF | Inflight entertainment is high AND Inflight WiFi service is low or medium AND Customer type is disloyal customer AND Flight distance is short THEN Passenger is neutral or dissatisfied |
No. | Fuzzy Classification Rules | |
---|---|---|
Solution No. 6 (, ): | ||
1–5. | These rules are the same as rules Nos. 1–5 from Solution No. 5. | |
6. | This rule is an extension of rule No. 6 from Solution No. 5: | |
IF | Inflight WiFi service is low or medium AND Type of travel is personal travel AND Flight distance is short AND Customer type is loyal customer THEN Passenger is neutral or dissatisfied | |
7–8. | These rules are the same as rules Nos. 7–8 from Solution No. 5. | |
9. | IF | Inflight WiFi service is low or medium AND Flight distance is short AND Customer type is disloyal customer THEN Passenger is neutral or dissatisfied |
10. | IF | Inflight WiFi service is low or medium AND Customer type is loyal customer AND Ease of online booking is high AND Leg room service is high THEN Passenger is satisfied |
11. | IF | Inflight WiFi service is low or medium AND Type of travel is personal travel AND Leg room service is low or medium THEN Passenger is neutral or dissatisfied |
Solution No. 7 (, ): | ||
1–5. | These rules are the same as rules Nos. 1–5 from Solution No. 6. | |
6. | This rule is an extension of rule No. 6 from Solution No. 4: | |
IF | Inflight WiFi service is low or medium AND Type of travel is personal travel AND Ease of online booking is no_answer or low THEN Passenger is neutral or dissatisfied | |
7–9. | These rules are the same as rules Nos. 7–9 from Solution No. 6. | |
10. | This rule is an extension of rule No. 1 from Solution No. 1: | |
IF | Inflight entertainment is no_answer or low AND Seat comfort is no_answer THEN Passenger is satisfied | |
11. | This rule is an extension of rule No. 6 from Solution No. 4: | |
IF | Inflight WiFi service is low or medium AND Type of travel is personal travel AND Ease of online booking is medium THEN Passenger is neutral or dissatisfied | |
12. | IF | Inflight WiFi service is no_answer AND Ease of online booking is no_answer or low THEN Passenger is satisfied |
13. | IF | On-board service is no_answer or low AND Seat comfort is no_answer THEN Passenger is satisfied |
14. | IF | On-board service is no_answer or low AND Seat comfort is low or medium THEN Passenger is neutral or dissatisfied |
15. | IF | On-board service is medium AND Leg room service is no_answer THEN Passenger is satisfied |
16. | IF | On-board service is high AND Ease of online booking is high AND Leg room service is high THEN Passenger is satisfied |
17. | IF | Seat comfort is low or medium AND Baggage handling is low or medium AND Checkin service is no_answer or low THEN Passenger is neutral or dissatisfied |
Attribute Name | , | Attribute Presence in the Rules of Solution No.: | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | |||
Part A—Number of input attributes: 21 | ||||||||||||
High | Inflight entertainment | 75.2% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ |
Seat comfort | +2.0% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||
■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||||
⟵ Attribute significance ⟶ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||||
Customer type | +2.3% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||||
Flight distance | +1.7% | ■ | ■ | ■ | ■ | ■ | ■ | |||||
■ | ■ | ■ | ■ | ■ | ||||||||
■ | ■ | ■ | ■ | ■ | ||||||||
■ | ■ | ■ | ■ | |||||||||
■ | ■ | ■ | ■ | |||||||||
■ | ■ | ■ | ■ | |||||||||
■ | ■ | ■ | ||||||||||
■ | ■ | ■ | ||||||||||
■ | ■ | |||||||||||
■ | ■ | |||||||||||
■ | ■ | |||||||||||
■ | ■ | |||||||||||
■ | ||||||||||||
Low | ■ | |||||||||||
■ | ||||||||||||
■ | ||||||||||||
Part B—Number of input attributes: 20 | ||||||||||||
High | Online boarding | 71.6% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ |
Ease of online booking | +3.7% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||
On-board service | +1.9% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||
⟵ Attribute significance ⟶ | Seat comfort | +2.9% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||
■ | ■ | ■ | ■ | ■ | ■ | |||||||
■ | ■ | ■ | ■ | ■ | ■ | |||||||
Customer type | +2.8% | ■ | ■ | ■ | ■ | ■ | ||||||
■ | ■ | ■ | ■ | |||||||||
■ | ■ | ■ | ■ | |||||||||
Baggage handling | +1.1% | ■ | ■ | ■ | ||||||||
■ | ■ | |||||||||||
■ | ■ | |||||||||||
■ | ■ | |||||||||||
■ | ||||||||||||
■ | ||||||||||||
■ | ||||||||||||
■ | ||||||||||||
Low | Class | |||||||||||
Departure/Arrival time conv. | ||||||||||||
Gate location | ||||||||||||
Part C—Number of input attributes: 19 | ||||||||||||
High | Ease of online booking | 69.0% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ |
Seat comfort | +2.6% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||
On-board service | +5.2% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||
⟵ Attribute significance ⟶ | Type of travel | +3.5% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||
Customer type | +2.4% | ■ | ■ | ■ | ■ | ■ | ■ | |||||
Inflight WiFi service | +0.9% | ■ | ■ | ■ | ■ | ■ | ||||||
■ | ■ | ■ | ■ | |||||||||
■ | ■ | ■ | ■ | |||||||||
Gender | +1.2% | ■ | ■ | ■ | ||||||||
■ | ■ | |||||||||||
■ | ■ | |||||||||||
■ | ■ | |||||||||||
■ | ||||||||||||
■ | ||||||||||||
■ | ||||||||||||
Cleanliness | ||||||||||||
Low | Checkin service | |||||||||||
Departure delay in minutes | ||||||||||||
Gate location |
Attribute Name | , | Attribute Presence in the Rules of Solution No.: | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | |||
Part D—Number of input attributes: 18 | ||||||||||||
High | Inflight WiFi service | 66.8% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ |
Seat comfort | +2.1% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||
Class | +6.7% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||||
⟵ Attribute significance ⟶ | Baggage handling | +2.8% | ■ | ■ | ■ | ■ | ||||||
■ | ■ | ■ | ||||||||||
■ | ■ | ■ | ||||||||||
■ | ■ | ■ | ||||||||||
■ | ■ | |||||||||||
■ | ■ | |||||||||||
■ | ||||||||||||
■ | ||||||||||||
■ | ||||||||||||
■ | ||||||||||||
On-board service | ||||||||||||
Food and drink | ||||||||||||
Low | Cleanliness | |||||||||||
Departure delay in minutes | ||||||||||||
Flight distance | ||||||||||||
Part E—Number of input attributes: 17 | ||||||||||||
High | Leg room service | 66.7% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ |
On-board service | +3.8% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||
⟵ Attribute significance ⟶ | Seat comfort | +3.3% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||
Type of travel | +1.4% | ■ | ■ | ■ | ■ | ■ | ■ | |||||
Baggage handling | +1.7% | ■ | ■ | ■ | ■ | ■ | ||||||
Customer type | +1.5% | ■ | ■ | ■ | ■ | |||||||
Gender | +2.8% | ■ | ■ | ■ | ||||||||
Flight distance | +0.0% | ■ | ■ | |||||||||
Cleanliness | +0.3% | ■ | ||||||||||
Class | ||||||||||||
Age | ||||||||||||
Departure/Arrival time conv. | ||||||||||||
Checkin service | ||||||||||||
Arrival delay in minutes | ||||||||||||
Low | Food and drink | |||||||||||
Gate location | ||||||||||||
Departure delay in minutes | ||||||||||||
Part F—Number of input attributes: 16 | ||||||||||||
High | On-board service | 66.3% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ |
■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||||
⟵ Attribute sign. ⟶ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||||
Customer type | +2.5% | ■ | ■ | ■ | ■ | ■ | ||||||
Type of travel | +3.3% | ■ | ■ | ■ | ||||||||
Baggage handling | +0.7% | ■ | ■ | |||||||||
Departure/Arrival time conv. | +1.4% | ■ | ||||||||||
Gender | ||||||||||||
Flight distance | ||||||||||||
Class | ||||||||||||
Age | ||||||||||||
Checkin service | ||||||||||||
Arrival delay in minutes | ||||||||||||
Low | Food and drink | |||||||||||
Gate location | ||||||||||||
Departure delay in minutes |
Attribute Name | , | Attribute Presence in the Rules of Solution No.: | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | |||
Part G—Number of input attributes: 15 | ||||||||||||
High | Seat comfort | 64.5% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ |
⟵ Attribute sign. ⟶ | Baggage handling | +2.7% | ■ | ■ | ■ | ■ | ■ | ■ | ||||
■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||||
■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||||
Customer type | +1.6% | ■ | ■ | ■ | ■ | ■ | ■ | |||||
Class | +0.7% | ■ | ■ | ■ | ||||||||
Age | +1.0% | ■ | ■ | |||||||||
Departure/Arrival time conv. | +0.1% | ■ | ||||||||||
Cleanliness | ||||||||||||
Gender | ||||||||||||
Checkin service | ||||||||||||
Arrival delay in minutes | ||||||||||||
Low | Food and drink | |||||||||||
Gate location | ||||||||||||
Departure delay in minutes | ||||||||||||
Part H—Number of input attributes: 14 | ||||||||||||
High | Cleanliness | 63.9% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ |
⟵ Attribute sign. ⟶ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||||
■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||||
Gender | +0.4% | ■ | ■ | ■ | ■ | ■ | ||||||
■ | ■ | ■ | ||||||||||
■ | ■ | ■ | ||||||||||
Gate location | +0.5% | ■ | ■ | |||||||||
■ | ||||||||||||
■ | ||||||||||||
■ | ||||||||||||
■ | ||||||||||||
Low | ■ | |||||||||||
Flight distance | ||||||||||||
Departure delay in minutes | ||||||||||||
Part I—Number of input attributes: 13 | ||||||||||||
High | Baggage handling | 63% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ |
⟵ Attr. sign. ⟶ | Type of travel | +4.3% | ■ | ■ | ■ | ■ | ■ | ■ | ||||
Class | +5.1% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ■ | |||
Flight distance | −0.1% | ■ | ■ | ■ | ■ | ■ | ■ | ■ | ||||
Customer type | +1.8% | ■ | ■ | ■ | ■ | ■ | ||||||
Departure/Arrival time conv. | +0.5% | ■ | ■ | ■ | ■ | |||||||
Gender | +1.8% | ■ | ■ | ■ | ||||||||
■ | ■ | |||||||||||
■ | ■ | |||||||||||
Food and drink | +0.2% | ■ | ||||||||||
Low | Checkin service | |||||||||||
Arrival delay in minutes | ||||||||||||
Departure delay in minutes |
Our Approach | Alternative Approach of [24] (Patlolla (2019)) | ||||||
---|---|---|---|---|---|---|---|
Attribute Name | Attribute Name | Importance | |||||
Attribute significance | ⟶High | Inflight entertainment | 75.2% | Inflight entertainment | 1.0 | ||
Online boarding | 71.6% | Class | 0.5206 | ||||
Ease of online booking | 69.0% | Inflight WiFi service | 0.4219 | ||||
Inflight WiFi service | 66.8% | Seat comfort | 0.3580 | ||||
Leg room service | 66.7% | Ease of online booking | 0.3333 | ||||
Low⟵ | On-board service | 66.3% | Leg room service | 0.2320 | |||
Seat comfort | 64.5% | Online boarding | 0.2099 | ||||
Cleanliness | 63.9% | Cleanliness | 0.1781 | ||||
Baggage handling | 63.0% | Type of travel | 0.1772 |
Source | Method | Learn-to- Test Ratio | Number of Runs | Average Accuracy | Average | ||||
---|---|---|---|---|---|---|---|---|---|
Measures for Learning and Test Data | Interpretability Measures | ||||||||
Patlolla (2019) | Decision tree | 7:3 | 1 | 84.0% | 84.0% | n/a | n/a | n/a | n/a |
This paper | Our approach based on: | ||||||||
SPEA2 | 1:9 | 10 | 88.1% | 88.0% | 16.8 | 14.3 | 28.5 | 3.1 | |
SPEA3 | 1:9 | 10 | 88.5% | 88.3% | 17.7 | 15.5 | 32.6 | 3.3 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Gorzałczany, M.B.; Rudziński, F.; Piekoszewski, J. Business Intelligence in Airline Passenger Satisfaction Study—A Fuzzy-Genetic Approach with Optimized Interpretability-Accuracy Trade-Off. Appl. Sci. 2021, 11, 5098. https://doi.org/10.3390/app11115098
Gorzałczany MB, Rudziński F, Piekoszewski J. Business Intelligence in Airline Passenger Satisfaction Study—A Fuzzy-Genetic Approach with Optimized Interpretability-Accuracy Trade-Off. Applied Sciences. 2021; 11(11):5098. https://doi.org/10.3390/app11115098
Chicago/Turabian StyleGorzałczany, Marian B., Filip Rudziński, and Jakub Piekoszewski. 2021. "Business Intelligence in Airline Passenger Satisfaction Study—A Fuzzy-Genetic Approach with Optimized Interpretability-Accuracy Trade-Off" Applied Sciences 11, no. 11: 5098. https://doi.org/10.3390/app11115098
APA StyleGorzałczany, M. B., Rudziński, F., & Piekoszewski, J. (2021). Business Intelligence in Airline Passenger Satisfaction Study—A Fuzzy-Genetic Approach with Optimized Interpretability-Accuracy Trade-Off. Applied Sciences, 11(11), 5098. https://doi.org/10.3390/app11115098