# A New User-Based Incentive Strategy for Improving Bike Sharing Systems’ Performance

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

## 1. Introduction

- Implementing and comparing existing spatial outlier detection algorithms for detecting outlier stations and testing them against three different scenarios. More specifically, we implemented the iterative r algorithm, the iterative z algorithm, the Median algorithm, the Z-score algorithm, the Moran scatterplot, and the Modified Moran scatterplot. These algorithms are compared in terms of their ability to enhance the BSS status.
- Developing a new user-based incentive method to enhance the BSS performance. The proposed method improves the resource availability of the BSS by adapting the departure and arrival stations of the users’ to the BSS state.
- Assessing the effectiveness of the new strategy using a real dataset issued from a well-known BSS called Velib.

## 2. Related Work

## 3. Study Area and Problem Definition

## 4. Rebalancing the Velib System

- Let A be the departure station of a journey, and B the arrival station of the journey. When a user chooses a station to rent or park a bike, the BSS application offers the user an incentive to relocate to other stations. When using the application, the user must specify if he is about to rent or park a bike, and the distance d that he is willing to walk to rent/park the bike $\in [400,500]$ m. This distance will be used to determine the neighbors of the original station chosen by the user.
- Then, the application checks whether the original station (A or B) is currently an isolated station. This is done by using a spatial outlier algorithm. Then, the application will propose to pay an incentive for the user if he accepts to modify his original station.
- The modification of the original station is carried out as follows: If the original station is A, the station will be substituted by the busiest station in the surrounding of A determined based on the d value, if and only if A is an isolated station. If the original station is B, the station will be substituted by the emptiest station in the surrounding of B determined according to the d value, if and only if B is an isolated station.

## 5. Experiments and Results

- Number of unbalanced (problematic) stations: This is the number of stations having a filling rate <10% or >90%, and thus, need to be balanced.
- Number of isolated stations: This describes the number of spatial outliers stations at a given time t $\in [1,24]$.
- Mean cumulative duration of station invalidity: This represents the amount of time during which the stations have no available bikes to rent or docks to use. The shorter the duration, the lower the probability of not meeting users’ needs.

- When there is no rebalancing strategy applied, we operate the BSS without any modification of the journeys.
- When the static rebalancing strategy is applied, the user gives his source and destination stations, respectively called A and B. Then, an alternative journey will be proposed for the user in which the new departure station is the busiest station around A and the new arrival station is the emptiest station around B [5]. With this strategy, A and B are always modified regardless of their states and the states of their neighbors.
- When the rebalancing strategy based on the rush hours is used, the same static rebalancing method described previously will be applied, but only during rush hours [6].

## 6. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Furness, Z. One Less Car: Bicycling and the Politics of Automobility; Temple University Press: Philadelphia, PA, USA, 2010; pp. 55–59. [Google Scholar]
- DeMaio, P.; Gifford, J. Will Smart Bikes Succeed as Public Transportation in the United States. J. Public Transp.
**2004**, 7, 1–15. [Google Scholar] [CrossRef] [Green Version] - Fishman, E. Bikeshare: A Review of Recent Literature. Transp. Rev.
**2016**, 36, 92–113. [Google Scholar] [CrossRef] - Zhang, Y.; Mi, Z. Environmental benefits of bike sharing: A big data-based analysis. Appl. Energy
**2018**, 220, 296–301. [Google Scholar] [CrossRef] - El Sibai, R.; Chabchoub, Y.; Fricker, C. Using spatial outliers detection to assess balancing mechanisms in bike sharing systems. In Proceedings of the 2018 IEEE 32nd International Conference on Advanced Information Networking and Applications (AINA), Krakow, Poland, 16–18 May 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 988–995. [Google Scholar]
- Chabchoub, Y.; El Sibai, R.; Fricker, C. Bike sharing systems: A new incentive rebalancing method based on spatial outliers detection. Int. J. Space Based Situated Comput.
**2019**, 9, 99–108. [Google Scholar] [CrossRef] [Green Version] - Ait-Ouahmed, A.; Josselin, D.; Zhou, F. Relocation optimization of electric cars in one-way car-sharing systems: Modeling, exact solving and heuristics algorithms. Int. J. Geogr. Inf. Sci.
**2018**, 32, 367–398. [Google Scholar] [CrossRef] [Green Version] - Illgen, S.; Höck, M. Literature review of the vehicle relocation problem in one-way car sharing networks. Transp. Res. Part B Methodol.
**2018**, 120, 193–204. [Google Scholar] [CrossRef] - Wong, W.K.; Moore, A.; Cooper, G.; Wagner, M. Rule-based anomaly pattern detection for detecting disease outbreaks. In Proceedings of the AAAI/IAAI, Edmonton, AB, Canada, 28 July—1 August 2002; pp. 217–223. [Google Scholar]
- Boudargham, N.; Abdo, J.B.; Demerjian, J.; Guyeux, C.; Atechian, T. Efficient cluster-based routing algorithm for body sensor networks. In Proceedings of the 2018 IEEE Middle East and North Africa Communications Conference (MENACOMM), Jounieh, Lebanon, 18–20 April 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 1–6. [Google Scholar]
- Boudargham, N.; El Sibai, R.; Abdo, J.B.; Demerjian, J.; Guyeux, C.; Makhoul, A. Toward fast and accurate emergency cases detection in BSNs. IET Wirel. Sens. Syst.
**2019**, 10, 47–60. [Google Scholar] [CrossRef] - Zhang, C.; Luo, L.; Xu, W.; Ledwith, V. Use of local Moran’s I and GIS to identify pollution hotspots of Pb in urban soils of Galway, Ireland. Sci. Total. Environ.
**2008**, 398, 212–221. [Google Scholar] [CrossRef] - Shekhar, S.; Lu, C.T.; Zhang, P. Detecting graph-based spatial outliers: Algorithms and applications (a summary of results). In Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 26–29 August 2001; ACM: New York, NY, USA, 2001; pp. 371–376. [Google Scholar]
- Chandola, V.; Banerjee, A.; Kumar, V. Anomaly detection: A survey. ACM Comput. Surv.
**2009**, 41, 15. [Google Scholar] [CrossRef] - El Sibai, R.; Bou Abdo, J.; Abou Jaoude, C.; Demerjian, J.; Assaker, J.; Makhoul, A. Efficient anomaly detection on sampled data streams with contaminated phase I data. Int. Technol. Lett.
**2020**, 3, e205. [Google Scholar] [CrossRef] - Chabchoub, Y.; Fricker, C. Classification of the vélib stations using Kmeans, Dynamic Time Wraping and DBA averaging method. In Proceedings of the 2014 International Workshop on Computational Intelligence for Multimedia Understanding (IWCIM), Paris, France, 1–2 November 2014; IEEE: Piscataway, NJ, USA, 2014; pp. 1–5. [Google Scholar]
- Etienne, C.; Latifa, O. Model-based count series clustering for bike sharing system usage mining: A case study with the Vélib’system of Paris. ACM Trans. Intell. Syst. Technol.
**2014**, 5, 1–21. [Google Scholar] [CrossRef] - Fricker, C.; Gast, N. Incentives and redistribution in homogeneous bike-sharing systems with stations of finite capacity. Eur. J. Transp. Logist.
**2016**, 5, 261–291. [Google Scholar] [CrossRef] [Green Version] - Froehlich, J.; Neumann, J.; Oliver, N. Sensing and predicting the pulse of the city through shared bicycling. IJCAI
**2009**, 9, 1420–1426. [Google Scholar] - Vogel, P.; Greiser, T.; Mattfeld, D.C. Understanding bike-sharing systems using data mining: Exploring activity patterns. Procedia Soc. Behav. Sci.
**2011**, 20, 514–523. [Google Scholar] [CrossRef] [Green Version] - Yi, P.; Huang, F.; Peng, J. A Rebalancing Strategy for the Imbalance Problem in Bike-Sharing Systems. Energies
**2019**, 12, 2578. [Google Scholar] [CrossRef] [Green Version] - Austwick, M.Z.; O’Brien, O.; Strano, E.; Viana, M. The structure of spatial networks and communities in bicycle sharing systems. PLoS ONE
**2013**, 8, 1–17. [Google Scholar] - Borgnat, P.; Abry, P.; Flandrin, P.; Robardet, C.; Rouquier, J.B.; Fleury, E. Shared bicycles in a city: A signal processing and data analysis perspective. Adv. Complex Syst.
**2011**, 14, 415–438. [Google Scholar] [CrossRef] [Green Version] - Gast, N.; Massonnet, G.; Reijsbergen, D.; Tribastone, M. Probabilistic forecasts of bike-sharing systems for journey planning. In Proceedings of the 24th ACM International Conference on Information and Knowledge Management, Melbourne, Australia, 19–23 October 2015; ACM: New York, NY, USA, 2015; pp. 703–712. [Google Scholar]
- Morton, C. Appraising the market for bicycle sharing schemes: Perceived service quality, satisfaction, and behavioural intention in London. Case Stud. Transp. Policy
**2018**, 6, 102–111. [Google Scholar] [CrossRef] [Green Version] - Nikitas, A. Understanding bike-sharing acceptability and expected usage patterns in the context of a small city novel to the concept: A story of ‘Greek Drama’. Transp. Res. Part F Traffic Psychol. Behav.
**2018**, 56, 306–321. [Google Scholar] [CrossRef] [Green Version] - Bakogiannis, E.; Siti, M.; Tsigdinos, S.; Vassi, A.; Nikitas, A. Monitoring the first dockless bike sharing system in Greece: Understanding user perceptions, usage patterns and adoption barriers. Res. Transp. Bus. Manag.
**2019**, 33, 100432. [Google Scholar] [CrossRef] - Nikitas, A. How to save bike-sharing: An evidence-based survival toolkit for policy-makers and mobility providers. Sustainability
**2019**, 11, 3206. [Google Scholar] [CrossRef] [Green Version] - Eren, E.; Uz, V.E. A review on bike-sharing: The factors affecting bike-sharing demand. Sustain. Cities Soc.
**2020**, 54, 101882. [Google Scholar] [CrossRef] - Ban, S.; Hyun, K.H. Designing a user participation-based bike rebalancing service. Sustainability
**2019**, 11, 2396. [Google Scholar] [CrossRef] [Green Version] - Singla, A.; Santoni, M.; Bartók, G.; Mukerji, P.; Meenen, M.; Krause, A. Incentivizing Users for Balancing Bike Sharing Systems. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI 2015), Austin, TX, USA, 25–30 January 2015; pp. 723–729. [Google Scholar]
- Chen, J.; Yang, Z.; Shu, Y.; Cheng, P. Rebalance Bike-Sharing System With Deep Sequential Learning. IEEE Intell. Transp. Syst. Mag.
**2020**, 1–7. [Google Scholar] [CrossRef] - Jin, X.; Tong, D. Station-Free Bike Rebalancing Analysis: Scale, Modeling, and Computational Challenges. ISPRS Int. J. Geo Inf.
**2020**, 9, 691. [Google Scholar] [CrossRef] - Freund, D.; Norouzi-Fard, A.; Paul, A.; Wang, C.; Henderson, S.G.; Shmoys, D.B. Data-driven rebalancing methods for bike-share systems. In Analytics for the Sharing Economy: Mathematics, Engineering and Business Perspectives; Springer: Berlin/Heidelberg, Germany, 2020; pp. 255–278. [Google Scholar]
- Ren, C.; An, L.; Gu, Z.; Wang, Y.; Gao, Y. Rebalancing the car-sharing system with reinforcement learning. World Wide Web
**2020**, 23, 2491–2511. [Google Scholar] [CrossRef] - Chemla, D.; Meunier, F.; Calvo, R.W. Bike sharing systems: Solving the static rebalancing problem. Discret. Optim.
**2013**, 10, 120–146. [Google Scholar] [CrossRef] - Forma, I.A.; Raviv, T.; Tzur, M. A 3-step math heuristic for the static repositioning problem in bike-sharing systems. Transp. Res. Part B Methodol.
**2015**, 71, 230–247. [Google Scholar] [CrossRef] - Dell’Amico, M.; Iori, M.; Novellani, S.; Subramanian, A. The bike sharing rebalancing problem with stochastic demands. Transp. Res. Part B Methodol.
**2018**, 118, 362–380. [Google Scholar] [CrossRef] - Chiariotti, F.; Pielli, C.; Zanella, A.; Zorzi, M. A dynamic approach to rebalancing bike-sharing systems. Sensors
**2018**, 18, 512. [Google Scholar] [CrossRef] [Green Version] - Faghih-Imani, A.; Hampshire, R.; Marla, L.; Eluru, N. An empirical analysis of bike sharing usage and rebalancing: Evidence from Barcelona and Seville. Transp. Res. Part A Policy Pract.
**2017**, 97, 177–191. [Google Scholar] [CrossRef] - Luo, H.; Zhao, F.; Chen, W.Q.; Cai, H. Optimizing bike sharing systems from the life cycle greenhouse gas emissions perspective. Transp. Res. Part C Emerg. Technol.
**2020**, 117, 102705. [Google Scholar] [CrossRef] - Cruz, F.; Subramanian, A.; Bruck, B.P.; Iori, M. A heuristic algorithm for a single vehicle static bike sharing rebalancing problem. Comput. Oper. Res.
**2017**, 79, 19–33. [Google Scholar] [CrossRef] [Green Version] - Haider, Z.; Nikolaev, A.; Kang, J.E.; Kwon, C. Inventory rebalancing through pricing in public bike sharing systems. Eur. J. Oper. Res.
**2018**, 270, 103–117. [Google Scholar] [CrossRef] - Pfrommer, J.; Warrington, J.; Schildbach, G.; Morari, M. Dynamic vehicle redistribution and online price incentives in shared mobility systems. arXiv
**2013**, arXiv:1304.3949. [Google Scholar] [CrossRef] [Green Version] - Legros, B. Dynamic repositioning strategy in a bike-sharing system; how to prioritize and how to rebalance a bike station. Eur. J. Oper. Res.
**2019**, 272, 740–753. [Google Scholar] [CrossRef] - Cressie, N. Straight line fitting and variogram estimation (with discussion). Bull. Int. Stat. Inst.
**1979**, 48, 573–582. [Google Scholar] - Cressie, N. Fitting variogram models by weighted least squares. J. Int. Assoc. Math. Geol.
**1985**, 17, 563–586. [Google Scholar] [CrossRef] - Haslett, J.; Bradley, R.; Craig, P.; Unwin, A.; Wills, G. Dynamic graphics for exploring spatial data with application to locating global and local anomalies. Am. Stat.
**1991**, 45, 234–242. [Google Scholar] - Akoglu, L.; Tong, H.; Koutra, D. Graph based Anomaly Detection and Description: A Survey. Data Min. Knowl. Discov.
**2015**, 29, 626–688. [Google Scholar] [CrossRef] [Green Version] - Anselin, L. The Moran Scatterplot as an ESDA Tool to Assess Local Instability in Spatial Association; Regional Research Institute, West Virginia University: Morgantown, WV, USA, 1993. [Google Scholar]
- Haining, R. Spatial Data Analysis in the Social and Environmental Sciences; Cambridge University Press: Cambridge, UK, 1993. [Google Scholar]
- Shekhar, S.; Lu, C.T.; Zhang, P. A unified approach to detecting spatial outliers. GeoInformatica
**2003**, 7, 139–166. [Google Scholar] [CrossRef] - Lu, C.T.; Chen, D.; Kou, Y. Algorithms for spatial outlier detection. In Proceedings of the Third IEEE International Conference on Data Mining, Melbourne, FL, USA, 22–22 November 2003; IEEE: Piscataway, NJ, USA, 2003; pp. 597–600. [Google Scholar]
- Qiu, L.Y.; He, L.Y. Bike Sharing and the Economy, the Environment, and Health-Related Externalities. Sustainability
**2018**, 10, 1145. [Google Scholar] [CrossRef] [Green Version] - Tout sur Vélib. 2014. Available online: http://blog.velib.paris.fr/blog/2014/07/15/7-ans-de-velib-des-records-de-frequentation-et-dabonnements/ (accessed on 2 January 2021).

**Figure 7.**Comparison of the number of isolated stations during the day for all the tested scenarios. Isolated stations are detected using the iterative r algorithm. The same algorithm is used to determine the stations to be replaced when the proposed rebalancing strategy is performed.

**Figure 8.**Comparison of the number of isolated stations during the day for all the tested scenarios. Isolated stations are detected using the iterative z algorithm. The same algorithm is used to determine the stations to be replaced when the proposed rebalancing strategy is performed.

**Figure 9.**Comparison of the number of isolated stations during the day for all the tested scenarios. Isolated stations are detected using the Median algorithm. The same algorithm is used to determine the stations to be replaced when the proposed rebalancing strategy is performed.

**Figure 10.**Comparison of the number of isolated stations during the day for all the tested scenarios. Isolated stations are detected using the Z-score algorithm. The same algorithm is used to determine the stations to be replaced when the proposed rebalancing strategy is performed.

**Figure 11.**Comparison of the number of isolated stations during the day for all the tested scenarios. Isolated stations are detected using the Moran Scatterplot algorithm. The same algorithm is used to determine the stations to be replaced when the proposed rebalancing strategy is performed.

**Figure 12.**Comparison of the number of isolated stations during the day for all the tested scenarios. Isolated stations are detected using the Modified Moran Scatterplot algorithm. The same algorithm is used to determine the stations to be replaced when the proposed rebalancing strategy is performed.

**Figure 13.**Comparison of the number of isolated stations during the day according to the used spatial outlier detection algorithm, when the proposed rebalancing strategy is used.

**Figure 14.**Evolution of the average number of unbalanced stations during the day according to the collaboration rate of the users.

Data Source | Velib Bike Sharing System |

Time | 1 day |

Number of Stations | 1397 |

Stations Information | ID, latitude, longitude, capacity |

Number of Journeys | 121,709 |

Number of Available Bikes and Docks | 40,051 |

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 (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

El Sibai, R.; Challita, K.; Bou Abdo, J.; Demerjian, J.
A New User-Based Incentive Strategy for Improving Bike Sharing Systems’ Performance. *Sustainability* **2021**, *13*, 2780.
https://doi.org/10.3390/su13052780

**AMA Style**

El Sibai R, Challita K, Bou Abdo J, Demerjian J.
A New User-Based Incentive Strategy for Improving Bike Sharing Systems’ Performance. *Sustainability*. 2021; 13(5):2780.
https://doi.org/10.3390/su13052780

**Chicago/Turabian Style**

El Sibai, Rayane, Khalil Challita, Jacques Bou Abdo, and Jacques Demerjian.
2021. "A New User-Based Incentive Strategy for Improving Bike Sharing Systems’ Performance" *Sustainability* 13, no. 5: 2780.
https://doi.org/10.3390/su13052780