# Research on the Purchase Intention of Electric Vehicles Based on Customer Evaluation and Personal Information

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

## 1. Introduction

- (1)
- Aimed at the micro-purchase factors of EVs, two influence factor analysis models are established, which determine the main factors influencing customers to purchase EVs from different brands.
- (2)
- Based on analyzing the influencing factors, the predictive purchase model of EVs is established, which can quickly predict the purchase intention of customers.
- (3)
- Based on the above research, the sales plan optimization model is established so as to propose a better sales plan.

## 2. Related Works

## 3. Data Processing

#### 3.1. Customer Experience Score Data (Data A)

_{1}, A

_{3}, A

_{5}, and A

_{7}. Then, data greater than 100 or less than 0 were replaced by linear interpolation, y

_{imod}:

_{i}is the corresponding serial number according to data A

_{i}and is arranged in ascending order, and y

_{i}is the abnormal score corresponding to x

_{i}. After correcting the data of all customers, relatively correct data can be obtained.

#### 3.2. Customer Personal Information Data (Data B)

_{4}and B

_{8}, groups B

_{13}, B

_{15}, B

_{16}, and B

_{17}, and groups B

_{5}, B

_{6}, and B

_{7}, where b

_{i}is the value of the i-th index in data B.

_{4}and B

_{8}, the customer cannot obtain a driver’s license until adulthood. Therefore, b

_{4}driving years should be less than or equal to the difference between the current time and the time from the b

_{8}birth year to adulthood:

_{13}, B

_{15}, B

_{16}, and B

_{17}, the criterion is that income must be greater than or equal to expenses:

_{15}does not satisfy Equation (3) and must be excluded. The excluded data are filled in using the family annual income rate and the individual annual income rate calculated from the normal data:

_{13}is the total family annual income and b

_{14}is the total individual annual income. K is the magnification ratio corresponding to b

_{13}data and b

_{14}data. By using the ergodic cycle method, the average rate $\overline{K}$ of all normal data is solved as follows:

_{15}that needs to be replaced is calculated:

_{5}), marital status (B

_{6}), and the number of children (B

_{7}) as a criterion; B

_{7}is set as a variable. Combined with Table 2, the values of B

_{5}, B

_{6}, and B

_{7}are adjusted, as shown in Table 3.

## 4. Methods

#### 4.1. ANOVA Analysis Model

_{r}is the ratio of intra-group and inter-group variances, and MSB is the mean square error between groups, that is, the sum of squares between groups divided by the degrees of freedom between groups. MSE is the mean square error within a group, which is the sum of squares divided by the group degree.

#### 4.2. Kruskal–Wallis Analysis Model

_{q}is the size of the samples in group q. The sum of the collected data is arranged in ascending order, and statistic H

_{r}is used to compare whether the population median of different samples is significantly different:

_{q}is the rank sum of the n

_{q}observations of group q (X

_{1}, …, X

_{q}).

#### 4.3. Random Forecast Purchase Forecast Model

_{1}, x

_{2}, …, x

_{u}). If a sample is taken from S and put back a total of u times to form a new set S*, then the probability of S* not containing sample x

_{s}(s = 1, 2, …, u) is as follows:

_{o}, t

_{cd}) of the impurity of the child node:

_{o}is the shred variable, t

_{cd}is the value of r

_{o}, y’

_{bag}(x

_{e}) is the impurity of the node, and α

_{l}, α

_{r}, and N

_{s}are the number of training samples of the left sub-node after segmentation, the number of training samples of the right sub-node, and the number of all training samples of the current node, respectively. x

_{l}and x

_{r}are the sets of training samples of the left and right sub-nodes, and M is the number of decision trees. After calculating the best segmentation variables and segmentation points in each decision tree, the training set and test set can be brought into the model for calculation. Finally, a prediction of the purchase can be obtained.

_{j}) is used to represent the entire correlation between the input and output results of the random forest method. Therefore, the probability that customers will purchase electric vehicles can be predicted as follows:

#### 4.4. Single Objective Linear Optimization Model of the Sales Plan

- (1)
- Assuming that the customer experience score data are equivalent to the service cost of the automobile sales company, increasing the customer experience score data score means increasing the service cost.
- (2)
- Considering the short-term improvement, it is assumed that the scores of data A increase in integer form, with a maximum increase of 5 for each item and a maximum score of 100.

- (1)
- Objective function

_{j}is the increased service score; j is [1,8].

- (2)
- Constraint condition

_{j}is the initial satisfaction score.

_{j}is the j-th satisfaction score of brand i. For the sake of optimization, v

_{j}is specified as an integer. v

_{j}can only be increased in the satisfaction score of data A, which means that v

_{j}belongs to data A. Moreover, the maximum v

_{j}is set to 5.

_{forecast}is greater than 0.5, the customer will buy the vehicle, and if P

_{forecast}is less than 0.5, the customer will not buy, so the constraint equation is as follows:

## 5. Results and Discussion

#### 5.1. Analysis of Influencing Factors

_{5}, B

_{7}, and B

_{8}(family size, number of children, and year of birth) have little impact. However, there are certain differences in the influence factors of different brands, among which B

_{16}and B

_{17}have a greater influence on the purchase of Brand 1 and Brand 2, and a relatively small influence on Brand 3. For further analysis, based on the results of the F model with 4% as the benchmark, the main influencing factors are screened out according to the proportion shown in Table 4.

_{3}); for Brand 2 (independent brand), customers are more concerned about the battery technical performance (A

_{1}); for Brand 3 (new power brand), customers are more concerned about the vehicle comfort performance (A

_{2}). In addition, car loans and mortgage loans have more influence on Brand 1 and less influence on Brand 3.

#### 5.2. EV Purchase Prediction

#### 5.3. Sales Plan Optimization

_{1}, A

_{3}, and A

_{5}, focus on introducing the battery performance, economy, and power of the company’s electric vehicles to customers during the sales process; this will significantly increase customer purchase intention and satisfaction. Similarly, for the sales of electric vehicles under Brand 2, if the focus is on introducing the battery performance and economic viability of the company’s electric vehicles to customers during the sales process, it will significantly increase their purchase intention and satisfaction. And, for the sales of electric vehicles under the third brand, during the sales process, the focus should be on introducing the comfort advantages of the company’s electric vehicles to customers; this will significantly increase customer purchase intention and satisfaction. In summary, for the above three electric vehicle brands or other electric vehicle companies, using the model established in this paper for sales strategy planning during the sales process can, to some extent, increase the number of electric vehicle customers and sales volume.

## 6. Conclusions

- (1)
- According to the logical relationships, the original data are processed, and the abnormal data are eliminated. The missing data are filled in by linear interpolation, average magnification, and other methods, and the reliability of the data is greatly improved.
- (2)
- The F and H models are used to analyze the influencing factors in the data. It was found that the results of the two test methods are consistent and mutually verified. For different EV brands, the main influencing factors of customer purchase are different, but on the whole, the customer experience score has a greater impact on EV purchase.
- (3)
- Based on the main influencing factors tested above, a customer purchase prediction model is established using the random forest method. The results show that the model is more accurate than other purchase prediction models, with the accuracy of all three brands exceeding 97%. In addition, 15 customer purchase intentions are predicted, and 6 customers will buy EVs.
- (4)
- Based on the customer prediction model, the single objective linear optimization model of the sales plan is established. The results showed that, with the optimized sales plan, the predicted purchase rate of test customers increased from 40% to 53%.

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Hartig, T.; Kahn, P.H. Living in Cities, Naturally. Science
**2016**, 352, 938–940. [Google Scholar] [CrossRef] [PubMed] - O’Brien, K. Political Agency: The Key to Tackling Climate Change. Science
**2015**, 350, 1170–1171. [Google Scholar] [CrossRef] [PubMed] - Brown, S.; Pyke, D.; Steenhof, P. Electric Vehicles: The Role and Importance of Standards in an Emerging Market. Energy Policy
**2010**, 38, 3797–3806. [Google Scholar] [CrossRef] - Yang, L.-F.; Xu, J.-H.; Neuhäusler, P. Electric Vehicle Technology in China: An Exploratory Patent Analysis. World Pat. Inf.
**2013**, 35, 305–312. [Google Scholar] [CrossRef] - Zhang, Y.; Zhong, M.; Geng, N.; Jiang, Y. Forecasting Electric Vehicles Sales with Univariate and Multivariate Time Series Models: The Case of China. PLoS ONE
**2017**, 12, e0176729. [Google Scholar] [CrossRef] [PubMed] - Tang, M.; Zhuang, W.; Li, B.; Liu, H.; Song, Z.; Yin, G. Energy-Optimal Routing for Electric Vehicles Using Deep Re-inforcement Learning with Transformer. Appl. Energy
**2023**, 350, 121711. [Google Scholar] [CrossRef] - Moy, K.; Ganapathi, D.; Geslin, A.; Chueh, W.; Onori, S. Synthetic Duty Cycles from Real-World Autonomous Electric Vehicle Driving. Cell Rep. Phys. Sci.
**2023**, 4, 101536. [Google Scholar] [CrossRef] - Bigerna, S.; Micheli, S. Attitudes toward Electric Vehicles: The Case of Perugia Using a Fuzzy Set Analysis. Sustainability
**2018**, 10, 3999. [Google Scholar] [CrossRef] - Habich-Sobiegalla, S.; Kostka, G.; Anzinger, N. Electric Vehicle Purchase Intentions of Chinese, Russian and Brazilian Citizens: An International Comparative Study. J. Clean. Prod.
**2018**, 205, 188–200. [Google Scholar] [CrossRef] - Higueras-Castillo, E.; Guillén, A.; Herrera, L.-J.; Liébana-Cabanillas, F. Adoption of Electric Vehicles: Which Factors are Really Important? Int. J. Sustain. Transp.
**2020**, 15, 799–813. [Google Scholar] [CrossRef] - Wang, Z.; Wang, C.; Hao, Y. Influencing Factors of Private Purchasing Intentions of New Energy Vehicles in China. J. Renew. Sustain. Energy
**2013**, 5, 063133. [Google Scholar] [CrossRef] - Carley, S.; Krause, R.M.; Lane, B.W.; Graham, J.D. Intent to Purchase a Plug-in Electric Vehicle: A Survey of Early Im-pressions in Large Us Cites. Transp. Res. Part D Transp. Environ.
**2013**, 18, 39–45. [Google Scholar] [CrossRef] - Klöckner, C.A. The Dynamics of Purchasing an Electric Vehicle–a Prospective Longitudinal Study of the Decision-Making Process. Transp. Res. Part F Traffic Psychol. Behav.
**2014**, 24, 103–116. [Google Scholar] [CrossRef] - Helveston, J.P.; Liu, Y.; Feit, E.M.; Fuchs, E.; Klampfl, E.; Michalek, J.J. Will Subsidies Drive Electric Vehicle Adoption? MEASURING Consumer Preferences in the U.S. and China. Transp. Res. Part A Policy Pract.
**2015**, 73, 96–112. [Google Scholar] [CrossRef] - Morton, C.; Anable, J.; Nelson, J.D. Exploring Consumer Preferences Towards Electric Vehicles: The Influence of Consumer Innovativeness. Res. Transp. Bus. Manag.
**2016**, 18, 18–28. [Google Scholar] [CrossRef] - Wang, Z.; Zhao, C.; Yin, J.; Zhang, B. Purchasing Intentions of Chinese Citizens on New Energy Vehicles: How Should One Respond to Current Preferential Policy? J. Clean. Prod.
**2017**, 161, 1000–1010. [Google Scholar] [CrossRef] - Degirmenci, K.; Breitner, M.H. Consumer Purchase Intentions for Electric Vehicles: Is Green more Important than Price and Range? Transp. Res. Part D Transp. Environ.
**2017**, 51, 250–260. [Google Scholar] [CrossRef] - Lane, B.W.; Dumortier, J.; Carley, S.; Siddiki, S.; Clark-Sutton, K.; Graham, J.D. All Plug-In Electric Vehicles are not the Same: Predictors of Preference for a Plug-In Hybrid Versus a Battery-Electric Vehicle. Transp. Res. Part D Transp. Environ.
**2018**, 65, 1–13. [Google Scholar] [CrossRef] - Li, W.; Long, R.; Chen, H.; Yang, T.; Geng, J.; Yang, M. Effects of Personal Carbon Trading on the Decision to Adopt Battery Electric Vehicles: Analysis Based on a Choice Experiment in Jiangsu, China. Appl. Energy
**2018**, 209, 478–488. [Google Scholar] [CrossRef] - Lin, B.; Wu, W. Why People want to Buy Electric Vehicle: An Empirical Study in First-Tier Cities of China. Energy Policy
**2018**, 112, 233–241. [Google Scholar] [CrossRef] - He, X.; Zhan, W.; Hu, Y. Consumer Purchase Intention of Electric Vehicles in China: The Roles of Perception and Personality. J. Clean. Prod.
**2018**, 204, 1060–1069. [Google Scholar] [CrossRef] - Du, H.; Liu, D.; Sovacool, B.K.; Wang, Y.; Ma, S.; Li, R.Y.M. Who Buys New Energy Vehicles in China? Assessing Social-Psychological Predictors of Purchasing Awareness, Intention, and Policy. Transp. Res. Part F Traffic Psychol. Behav.
**2018**, 58, 56–69. [Google Scholar] [CrossRef] - Ma, S.-C.; Fan, Y.; Guo, J.-F.; Xu, J.-H.; Zhu, J. Analysing Online Behaviour to Determine Chinese Consumers’ Preferences for Electric Vehicles. J. Clean. Prod.
**2019**, 229, 244–255. [Google Scholar] [CrossRef] - Okada, T.; Tamaki, T.; Managi, S. Effect of Environmental Awareness on Purchase Intention and Satisfaction Pertaining to Electric Vehicles in Japan. Transp. Res. Part D Transp. Environ.
**2019**, 67, 503–513. [Google Scholar] [CrossRef] - Huang, X.; Ge, J. Electric vehicle development in Beijing: An analysis of consumer purchase intention. J. Clean. Prod.
**2019**, 216, 361–372. [Google Scholar] [CrossRef] - Habich-Sobiegalla, S.; Kostka, G.; Anzinger, N. Citizens’ electric vehicle purchase intentions in China: An analysis of micro-level and macro-level factors. Transp. Policy
**2019**, 79, 223–233. [Google Scholar] [CrossRef] - Carley, S.; Siddiki, S.; Nicholson-Crotty, S. Evolution of Plug-in Electric Vehicle Demand: Assessing Consumer Per-ceptions and Intent to Purchase over Time. Transp. Res. Part D Transp. Environ.
**2019**, 70, 94–111. [Google Scholar] [CrossRef] - Chen, K.; Ren, C.; Gu, R.; Zhang, P. Exploring Purchase Intentions of New Energy Vehicles: From the Perspective of Frugality and the Concept of “Mianzi”. J. Clean. Prod.
**2019**, 230, 700–708. [Google Scholar] [CrossRef] - Wang, L.; Fu, Z.-L.; Guo, W.; Liang, R.-Y.; Shao, H.-Y. What Influences Sales Market of New Energy Vehicles in China? Empirical Study Based on Survey of Consumers’ Purchase Reasons. Energy Policy
**2020**, 142, 111484. [Google Scholar] [CrossRef] - Jayasingh, S.; Girija, T.; Arunkumar, S. Factors Influencing Consumers’ Purchase Intention Towards Electric Two-Wheelers. Sustainability
**2021**, 13, 12851. [Google Scholar] [CrossRef] - He, Z.; Zhou, Y.; Wang, J.; Shen, W.; Li, W.; Lu, W. Influence of Emotion on Purchase Intention of Electric Vehicles: A Comparative Study of Consumers with Different Income Levels. Curr. Psychol.
**2022**, 42, 21704–21719. [Google Scholar] [CrossRef] [PubMed] - Ji, D.; Gan, H. Effects of Providing Total Cost of Ownership Information on Below-40 Young Consumers’ Intent to Purchase an Electric Vehicle: A Case Study in China. Energy Policy
**2022**, 165, 112954. [Google Scholar] [CrossRef] - HSBMMC. “Huashu Cup” National College Student Mathematical Modeling Competition, Question C, 2021st ed.; Big Data and Mathematical Model Professional Committee of China Future Research Association: Tianjin, China, 2021. [Google Scholar]
- Ozcelik, B.; Erzurumlu, T. Comparison of the Warpage Optimization in the Plastic Injection Molding Using Anova, Neural Network Model and Genetic Algorithm. J. Mater. Process. Technol.
**2006**, 171, 437–445. [Google Scholar] [CrossRef] - Guo, S.; Zhong, S.; Zhang, A. Privacy-Preserving Kruskal–Wallis Test. Comput. Methods Programs Biomed.
**2013**, 112, 135–145. [Google Scholar] [CrossRef] - Hoarau, A.; Martin, A.; Dubois, J.-C.; Le Gall, Y. Evidential Random Forests. Expert Syst. Appl.
**2023**, 230, 120652. [Google Scholar] [CrossRef] - Wang, Z.; Liang, Z.; Zeng, R.; Yuan, H.; Srinivasan, R.S. Identifying the Optimal Heterogeneous Ensemble Learning Model for Building Energy Prediction Using the Exhaustive Search Method. Energy Build.
**2023**, 281, 112763. [Google Scholar] [CrossRef] - Yang, Q.; Guo, X.; Zheng, H.; Dong, W. Single- and Multi-Objective Optimization of an Aircraft Hot-Air Anti-Icing System Based on Reduced Order Method. Appl. Therm. Eng.
**2023**, 219, 119543. [Google Scholar] [CrossRef]

**Figure 1.**Data A filtered by the box plot method. Red "+" in the figure represents the satisfaction scores in data A.

**Figure 4.**Data group 25 normal distribution probability graph. Blue "+" in the figure represent the probability of values in data A

_{7}. The dotted red line reflects the degree to which the data conform to a normal distribution.

Data A | Data B | ||||
---|---|---|---|---|---|

Index | Implication | Index | Implication | Index | Implication |

A_{1} | Battery performance | B_{1} | Residence | B_{10} | Working years |

A_{2} | Comfort | B_{2} | City residency time | B_{11} | Kind of working unit |

A_{3} | Economy | B_{3} | Residence zone | B_{12} | Job title |

A_{4} | Security | B_{4} | Driving years | B_{13} | Household income |

A_{5} | Power | B_{5} | Number of family members | B_{14} | Personal income |

A_{6} | Vehicle handling | B_{6} | Marital status | B_{15} | Household disposable annual income |

A_{7} | Exterior and interior | B_{7} | Number of children | B_{16} | Annual proportion of house loan |

A_{8} | Configuration and quality | B_{8} | Year of birth | B_{17} | Annual proportion of car loans |

\ | \ | B_{9} | Educational background | \ | \ |

Index | Value | Implication |
---|---|---|

B_{5} | 1, 2, 3… | Family size |

B_{6} | 1 | Unmarried, living alone |

2 | Unmarried, living with parents | |

3 | Married, no children, not living with parents | |

4 | Married, no children, living with parents | |

5 | Married, children, not living with parents | |

6 | Married, children, not living with parents | |

7 | Divorced/widowed | |

8 | Others | |

B_{7} | 0, 1, 2, 3… | Number of children |

Raw Data | Processing | ||
---|---|---|---|

B_{7} | B_{6} | B_{5} | |

1 | ≤4 | Arbitrary | Change B_{7} to 0 |

5 | 3 | Normal | |

6 | ≤3 | Change B_{5} to 5 | |

4 < B_{5} < 9 | Normal | ||

2 | <4 | Arbitrary | Change B_{7} to 0 |

5 | 4 | Normal | |

6 | ≤4 | Change B_{5} to 6 | |

4 < B_{5} < 7 | Normal | ||

3 | 5 | <5 | Change B_{5} to 5 |

5 | Normal | ||

6 | 6 | Normal | |

Not filled | Arbitrary | Arbitrary | Change B_{7} to 0 |

Brand 1 | Brand 2 | Brand 3 |
---|---|---|

A_{3} | A_{1} | A_{2} |

B_{17} | A_{5} | A_{3} |

A_{1} | A_{3} | A_{5} |

B_{16} | A_{2} | A_{1} |

A_{2} | A_{4} | A_{6} |

A_{6} | A_{7} | A_{8} |

A_{5} | B_{16} | A_{4} |

A_{4} | A_{6} | A_{7} |

A_{7} | A_{8} | B_{16} |

A_{8} | B_{17} | |

B_{15} |

Training Set Accuracy | Test Set Accuracy | Maximum Number of Splits | Number of Learners | |
---|---|---|---|---|

Brand 1 | 99.40% | 97.80% | 389 | 50 |

Brand 2 | 99.70% | 98.90% | 1272 | 50 |

Brand 3 | 98.90% | 97.60% | 136 | 50 |

Customer ID | Brand | P_{forecast} | Forecast |
---|---|---|---|

1 | 1 | 0.840 | Buy |

2 | 1 | 0.510 | Buy |

3 | 1 | 0.000 | No |

4 | 1 | 0.285 | No |

5 | 1 | 0.060 | No |

6 | 2 | 0.660 | Buy |

7 | 2 | 0.520 | Buy |

8 | 2 | 0.000 | No |

9 | 2 | 0.000 | No |

10 | 2 | 0.272 | No |

11 | 3 | 0.520 | Buy |

12 | 3 | 0.920 | Buy |

13 | 3 | 0.000 | No |

14 | 3 | 0.000 | No |

15 | 3 | 0.459 | No |

Brand | v_{1} | v_{2} | v_{3} | v_{4} | v_{5} | v_{6} | v_{7} | v_{8} | g |
---|---|---|---|---|---|---|---|---|---|

1 | 1 | 0 | 3 | 0 | 1 | 0 | 0 | 0 | 5 |

2 | 3 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 4 |

3 | 0 | 5 | 0 | 0 | 0 | 0 | 0 | 0 | 5 |

Customer ID | 3 | 4 | 5 | 8 | 9 | 10 | 13 | 14 | 15 | |
---|---|---|---|---|---|---|---|---|---|---|

P_{forecast} | Before optimization | 0 | 0.285 | 0.06 | 0 | 0 | 0.272 | 0 | 0 | 0.459 |

After optimization | 0.16 | 0.4 | 0.133 | 0.2 | 0.14 | 0.52 | 0.05 | 0.32 | 0.52 |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2023 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

**MDPI and ACS Style**

Chen, J.; Zhang, Z.; Zhao, C.; Zhang, S.; Guo, W.; Lu, C.; Sun, X.
Research on the Purchase Intention of Electric Vehicles Based on Customer Evaluation and Personal Information. *World Electr. Veh. J.* **2024**, *15*, 9.
https://doi.org/10.3390/wevj15010009

**AMA Style**

Chen J, Zhang Z, Zhao C, Zhang S, Guo W, Lu C, Sun X.
Research on the Purchase Intention of Electric Vehicles Based on Customer Evaluation and Personal Information. *World Electric Vehicle Journal*. 2024; 15(1):9.
https://doi.org/10.3390/wevj15010009

**Chicago/Turabian Style**

Chen, Jian, Zhenshuo Zhang, Chenyu Zhao, Shuai Zhang, Wenfei Guo, Cunhao Lu, and Xiaoguang Sun.
2024. "Research on the Purchase Intention of Electric Vehicles Based on Customer Evaluation and Personal Information" *World Electric Vehicle Journal* 15, no. 1: 9.
https://doi.org/10.3390/wevj15010009