Apriori Algorithm in Mining Common Technical Actions in

Competitions

Yong Cheng

Yunnan Engineering Vocational College, Kunming, 650000, China

Keywords: Basketball Technology, Apriori Algorithm, Basketball Games, Passing Between Marches.

Abstract: The application of basketball technology in basketball games is crucial, but there are unreasonable running

and defensive problems. Basic technique teaching does not solve the problem of passing between the marches

of basketball games, and the evaluation is not reasonable. Therefore, this paper proposes an Apriori algorithm

for technical analysis of passing between marches. Firstly, statistical theory is used to evaluate athletes, and

indicators are divided according to the requirements of basketball technical actions to reduce the interference

factors in basketball technical actions. Then, the statistical theory evaluates the passing technique between the

athletes, forms a basketball technical action mining scheme, and comprehensively analyzes the basketball

technical action mining results. MATLAB simulation shows that under certain evaluation criteria, the

technical strategy and confrontation of Apriori algorithm for

passing between athletes are better than basic

technical teaching.

1 INTRODUCTION

Passing accuracy is one of the important contents of

passing between athletes, which is of crucial

significance to athletes' competitive ability (Aksovic,

and Dobrescu, et al. 2023). However, in the process

of technical action training, the basketball technical

action mining scheme has the problem of poor

strategy, which brings a certain loss rate to the

athletes' games (Aras and Onlu,, et al. 2023). Some

scholars believe that the application of Apriori

algorithm to the teaching analysis of passing between

athletes can effectively analyze the basketball

technical action mining scheme and provide

corresponding support for technical action training

(Bowman and Harmon, et al. 2023). On this basis, this

paper proposes that the Apriori algorithm optimizes

the basketball technical action mining scheme and

verifies the effectiveness of the model (Choi and Cho,

et al. 2023). Basketball is a highly technical sport that

requires players to have a variety of skills (Chu and

Lin , et al. 2023), such as dribbling, passing, shooting,

defense, and more (Chun and Lee, et al. 2023). For

coaching coaches, it is not only necessary to

understand the basic skills of athletes, but also to

master certain guidance skills and teaching methods

(Csurilla and Boros, et al. 2023). This paper will

introduce the application of Aprionri algorithm in

basketball game action recognition and its

optimization method, and discuss the application of

common techniques in design (Pedro-Munez and

Alvarez-Yates, et al. 2023).

1.1 Application of Aprionri Algorithm

in Basketball Game Action

Recognition

Aprionri's algorithm is a commonly used machine

learning algorithm that trains on existing datasets and

identifies new samples (El-Saleh, 2023). In basketball

game action recognition, the algorithm can be trained

through previously acquired datasets to identify

different types of actions performed by players during

the game (Ferioli and Conte, et al. 2023). In the

application of Aprionri's algorithm, its optimization

methods include:

1.1.1 Data Preprocessing

Before applying the Aprionri algorithm for basketball

game action recognition, the data needs to be

preprocessed. For example, by segmenting and

labeling the game video, the start and end time of each

action is obtained for subsequent data processing and

analysis (Ferioli and Conte, et al. 2023).

418

Cheng, Y.

Apriori Algorithm in Mining Common Technical Actions in Competitions.

DOI: 10.5220/0013544700004664

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 1, pages 418-424

ISBN: 978-989-758-763-4

1.1.2 Feature Extraction

For each action in a basketball game video, some

features need to be extracted as input to the algorithm.

These features, including the trajectory of the object,

the shape and size of the moving object, the body

posture of the player, and so on, can be used to judge

different types of actions and improve the accuracy of

the algorithm (Ferioli, and Rampinini, et al. 2023).

1.1.3 Algorithm Improvements

Improvements can be made from the Aprionri

algorithm, for example, we can adopt the fuzzy

Aprionri algorithm to further improve the accuracy of

recognition, or use sequence models to further

enhance the performance of the algorithm

(Goldschmied, and Raphaeli, et al. 2023).

1.1.4 Data Processing

The data processing of basketball game action

technology mainly includes data cleaning, data

collection, data mining, data analysis and data

visualization (Gou, and Li, 2023).

Data cleansing refers to the preliminary

processing of raw data to remove invalid and

duplicate data. Through data cleaning, the quality and

accuracy of data can be improved, and a good

foundation can be laid for subsequent data processing

and application (Horvat, and Job, et al. 2023).

Data collection refers to the collection and

collation of cleaned data. Through data collection,

more data information can be obtained, and different

types and sources of data can be uniformly formatted

and standardized for subsequent data mining and

analysis (Ibanez and Pinar, et al. 2023).

Data mining refers to the deep mining and

analysis of data to reveal hidden patterns, patterns,

and trends in the data. Data mining can help us better

understand the technical status and level of athletes,

and provide athletes with more accurate technical

guidance and training.

Data analysis refers to the analysis of the

excavated data to verify whether the results and

conclusions of the data analysis are correct (Jane and

Chen, et al. 2023). Data analysis can help us better

understand the technical status and characteristics of

basketball players, and provide coaches with more

comprehensive, in-depth and convincing technical

guidance and training advice (Jin and Ge et al. 2023).

Data visualization is a data visualization tool that

presents data in a graphical or graphical form to

facilitate more intuitive understanding and analysis of

data. Data visualization can also help coaches better

understand the technical status and characteristics of

athletes, and provide coaches with more

comprehensive and in-depth technical guidance and

training suggestions (Koba and Nagel, et al. 2023).

1.2 Application Areas

The application fields of basketball game action

technology data mining mainly include the following

aspects:

1.2.1 Technical Guidance and Training

Technical guidance and training of basketball players

is one of the main application fields of data mining.

Through data mining, you can understand the

technical performance and shortcomings of each

athlete, develop personalized training plans and

teaching programs, and improve the technical level of

athletes.

1.2.2 Team Management and Game

Strategy

The management and operation of basketball games

is also one of the important application fields of data

mining. Through data mining of team members, game

status and opponent information, more scientific and

reasonable game strategies can be formulated for the

team to improve the team's combat effectiveness and

competitiveness.

1.2.3 Scientific Research and Theoretical

Research

Basketball game action technology data mining is

also one of the important application fields of

scientific research and theoretical research. Through

in-depth excavation and analysis of the action

technology in basketball games, the laws and

characteristics of the action technology can be

explored, and more scientific and accurate theoretical

support can be provided for basketball teaching and

sports training.

1.3 Application of Common

Techniques in Basketball Design

In recent years, with the continuous development of

science and technology, various high-tech

technologies have begun to penetrate into all aspects

of basketball teaching and guidance. The following

describes the application of common techniques in

basketball design.

Apriori Algorithm in Mining Common Technical Actions in Competitions

419

1.3.1 VR Technology

VR technology can provide players with a more

realistic and immersive basketball training

experience. By simulating different scenarios and

environments, players can more intuitively

understand basketball techniques, tactics and

strategies.

1.3.2 3D Printing Technology

3D printing technology can help players better

understand and master details such as the trajectory

of the ball, the shape and size of the ball, and so on.

In addition, players can also print their arms, hands

and toes through 3D printing technology to better

practice their skills and movements.

1.3.3 Sensor Technology

Sensor technology can be used to monitor and record

the movement status of players in real time. By

monitoring athletes' posture, speed, acceleration and

other indicators, coaches can better understand the

training effect of players and analyze players'

performance in the game.

1.3.4 AI Technology

In teaching and guidance, AI technology can provide

better services for coaches. Through AI technology,

coaches can personalize the training of players,

develop training plans and teaching programs suitable

for players, and better promote the technical

improvement of players.

2 RELATED CONCEPTS

2.1 Mathematical Description of

Apriori's Algorithm

Apriori algorithm uses simulation theory to optimize

the basketball technical action mining scheme, and

finds the substandard value of basketball games

according to the indicators in technical actions, and

integrates the basketball technical action mining

scheme to finally judge the feasibility of passing

teaching between athletes. Apriori's algorithm

combines the advantages of simulation theory and

quantifies it by using the passing teaching between

athletes' marches, which can improve the passing

accuracy of basketball technical movements.

Hypothesis 1: The basketball technical action

requirements is

, the basketball technical action

mining scheme is

set , the satisfaction of the

basketball technical action mining scheme is

, and

the judgment function of the basketball technical

action mining scheme is

(0)

Dx≈ ，as shown in

Equation (1).

() 6

iii i

Dd X x y

=→ →⋅









)

2.2 Selection of Passing Accuracy

Scheme

Hypothesis 2: The teaching function of passing

between the marches of athletes is

, and the weight

coefficient is

w , then, the teaching of passing

between the marches of athletes who do not meet the

requirements of basketball technical actions is

shown in Equation (2).

j( )=w ( , ) lim ( )

ii ii ii

Fd y d z

→

⋅−⋅⋅

∏

)

2.3 Analysis of Basketball Technical

Action Mining Scheme

Before carrying out the Apriori algorithm, a multi-

dimensional analysis of the basketball technical

action mining scheme should be carried out, and the

basketball technical action requirements should be

mapped to the athletes' passing teaching library

between marches, and the basketball technical action

mining scheme that does not meet the standard should

be eliminated. First, a comprehensive analysis of the

passing teaching between the marches of the athletes,

and the threshold and index weight of the basketball

technical action mining scheme are set to ensure the

strategic nature of the Apriori algorithm. The

teaching of passing between athletes is a systematic

test of basketball technical action mining scheme,

which needs to be standardized analysis. If the

passing teaching of athletes is in a non-normal

distribution, the mining scheme of basketball

technical actions will be affected, reducing the

strategic nature of the overall basketball technical

actions. In order to improve the strategicity of

INCOFT 2025 - International Conference on Futuristic Technology

420

Apriori's algorithm and improve the level of

basketball technical actions, it is necessary to select

the basketball technical action mining scheme, and

the specific scheme selection is shown in Figure 1.

Moving pass

Basketball

technique

Two-handed chest

pass

One handed side

pass

One-handed

shoulder pass

Figure 1: Results of selection of the passing accuracy

scheme

The investigation of basketball technical action

mining scheme shows that the passing accuracy

scheme shows a multi-dimensional distribution,

which is in line with objective facts. The teaching of

passing between athletes is not directional, indicating

that the passing accuracy scheme has strong

randomness, so it is regarded as a high analytical

study. The teaching of passing between the marches

of athletes meets the requirements of normality,

mainly because the simulation theory adjusts the

teaching of passing between the marches of athletes,

removes the repetitive and irrelevant schemes, and

supplements the default scheme, so that the dynamic

correlation of the whole basketball technical action

mining scheme is strong.

3 OPTIMIZATION STRATEGY

OF PASSING TEACHING

BETWEEN ATHLETES

Apriori algorithm adopts a random optimization

strategy for the teaching of passing between athletes,

and adjusts the parameters of athletes to optimize the

scheme of passing teaching between athletes.

Apriori's algorithm divides the passing teaching of

athletes between marches into different basketball

technical action levels, and randomly selects different

schemes. In the iterative process, the basketball

technical action mining scheme of different

basketball technical action levels was optimized and

analyzed. After the optimization analysis is

completed, the basketball technical action level of

different schemes is compared, and the best athlete

passing teaching between marches is recorded.

4 PRACTICAL EXAMPLES OF

PASSING TEACHING

BETWEEN ATHLETES

4.1 Introduction to Basketball

Technical Movements

In order to facilitate the analysis of basketball

technical movements, this paper takes the teaching of

athletes passing between marches under complex

conditions as the research object, with 12 paths and a

test time of 12h 1. shown.

Table 1: College basketball technical action requirements

Scope of

lication

action Specification

effect

Passing

accurac

Class I

athlete

Ball 78.44 79.60

Shooting 79.35 78.50

Level 2

athletes

Ball 76.61 79.85

Shooting 77.84 80.42

Class III

athlete

Ball 81.66 78.41

Shooting 76.52 79.84

The basketball technique action process in Table

1. is shown in Figure 2.

Sense of balance

sensitivity

Jumping force

Reaction rate

Spatial sense

Figure 2: Analysis process of passing teaching between

athletes' marches

Apriori Algorithm in Mining Common Technical Actions in Competitions

421

Compared with basic technical teaching, the

basketball technical action mining scheme of Apriori

algorithm is closer to the actual technical action

requirements. In terms of the rationality and

fluctuation range of the teaching of passing between

athletes, the basic technique of Apriori algorithm is

taught. It can be seen from the change of basketball

technology action mining scheme in Figure II that the

stability of Apriori algorithm is better and the

judgment speed is faster. Therefore, the basketball

technical action mining scheme of Apriori algorithm

has better speed, passing accuracy scheme, basketball

technical action mining scheme, and summation

stability.

4.2 Teaching of Passing Between

Athletes' Marches

The basketball technique action mining scheme for

athletes' passing teaching between marches includes

non-structural information, semi-structural

information and structural information. After the pre-

selection of Apriori algorithm, a preliminary

basketball technical action mining scheme for

athletes' passing teaching between marches was

obtained, and the feasibility of the basketball

technical action mining scheme for athletes' passing

teaching between marches was analyzed. In order to

more accurately verify the effect of athletes' inter-

march passing teaching norms, select the teaching of

cross-marching balls between athletes with different

basketball technical action levels, and the basketball

technical action mining scheme is shown in Table 2.

Table 2: The overall picture of the passing accuracy scheme

Cate

Scorin

rate Passin

rate

Shootin

88.95 87.55

Ball 87.20 90.90

Pass 90.20 87.72

mean 87.41 85.24

76.52 79.84

P=2.078

4.3 Passing Accuracy and Stability of

Basketball Technical Movements

In order to verify the strategy of Apriori algorithm,

compared with the basketball technical action mining

scheme for basic technology teaching, the basketball

technical action mining scheme is shown in Figure 3.

Figure 3: Passing accuracy of different algorithms

It can be seen from Figure 3 that the passing

accuracy of Apriori algorithm is higher than that of

basic technical teaching, but the error rate is lower,

indicating that the basketball technical action of

Apriori algorithm is relatively stable, while the

basketball technical action of basic technical teaching

is uneven. The average basketball technique action

mining scheme of the above three algorithms is

shown in Table 3.

Table 3: Strategic comparison of basketball techniques and

actions of different methods'

Algorithm Dribble Long

iograph

Flip the ball

Apriori

orith

89.92 90.43 87.85

Basic

technical

teaching

90.07 90.79 93.12

P 76.73 82.29 78.60

It can be seen from Table 3 that the basic

technique teaching has deficiencies in the accuracy

and stability of passing between athletes, and the

teaching of passing between athletes has changed

significantly, and the error rate is high. The general

results of Apriori's algorithm have higher passing

accuracy and are better than basic technique teaching.

At the same time, the passing accuracy of Apriori's

algorithm is greater than 90%, and the accuracy has

not changed significantly. In order to further verify

the superiority of Apriori's algorithm. In order to

further verify the effectiveness of the proposed

method, the general analysis of Apriori algorithm is

performed with different methods, as shown in Figure

INCOFT 2025 - International Conference on Futuristic Technology

422

Figure 4: Apriori algorithmic ball technique moves with

passing accuracy

It can be seen from Figure 4 that the passing

accuracy of Apriori algorithm is significantly better

than that of basic technique teaching, and the reason

is that Apriori algorithm increases the adjustment

coefficient of passing teaching between athletes, sets

the threshold of athletes, and eliminates the basketball

technical action mining scheme that does not meet the

requirements.

5 CONCLUSIONS

Aiming at the problem that the passing accuracy of

athletes' passing between marches is not satisfactory,

this paper proposes an Apriori algorithm, and

combines simulation theory to optimize the passing

teaching between athletes. At the same time, the

basketball technical action specifications and

threshold specifications are analyzed in depth to

construct a collection of athletes. The research shows

that the Apriori algorithm can improve the accuracy

and stability of the passing teaching between the

marches, and can perform general basketball

technical actions for the passing teaching between the

athletes. However, in the process of Apriori

algorithm, too much attention is paid to the analysis

of basketball technical actions, resulting in

irrationality in the selection of basketball technical

action indicators.

REFERENCES

Aksovic, N., Dobrescu, T., Bubanj, S., Bjelica, B.,

Milanovic, F., Kocic, M., Zelenovic, M., Radenkovic,

M., Nurkic, F., Nikolic, D., Markovic, J., Tomovic, M.,

& Vulpe, A.-M.(2023) Sports Games and Motor Skills

in Children, Adolescents and Youth with Intellectual

Disabilities. Children-Basel, 10(6):1.

Aras, D., Onlu, A. S., Durmus, T., Cengiz, C., Guler, D.,

Guler, Y., Ugurlu, A., Aldhahi, M. I. I., & Gulu,

M.(2023) A brief body scan mindfulness practice has

no positive effect on the recovery of heart rate

variability and cognitive tasks in female professional

basketball players. Frontiers in Psychology, 14(3):43.

Bowman, R. A., Harmon, O., & Ashman, T.(2023)

Schedule inequity in the National Basketball

Association. Journal of Sports Analytics, 9(1): 61-76.

Choi, T., Cho, K., & Sung, Y.(2023) Approaches That Use

Domain-Specific Expertise: Behavioral-Cloning-Based

Advantage Actor-Critic in Basketball Games.

Mathematics, 11(5):33.

Chu, E. C.-P., Lin, A. F. C., Mok, S., Piong, S. T., & Ng,

G.(2023) A Central Slip Injury in a Professional

Basketball Player. Cureus Journal of Medical Science,

15(2):45.

Chun, D.-R., Lee, M.-Y., Kim, S.-W., Cho, E.-Y., & Lee,

B.-H.(2023) The Mediated Effect of Sports Confidence

on Competitive State Anxiety and Perceived

Performance of Basketball Game. International Journal

of Environmental Research and Public Health, 20(1):2.

Csurilla, G., Boros, Z., Furesz, D. I., Gyimesi, A., Raab, M.,

& Sterbenz, T.(2023) How Much Is Winning a Matter

of Luck? A Comparison of 3 * 3 and 5v5 Basketball.

International journal of environmental research and

public health, 20(4):4.

Pedro-Munez, A., Alvarez-Yates, T., Serrano-Gomez, V.,

& Garcia-Garcia, O.(2023) Intraseason Changes in

Vertical Jumps of Male Professional Basketball

Players. International journal of environmental research

and public health, 20(6):78.

El-Saleh, M. S.(2023) The Effect of an Educational

Program for Mental Visualization to Teaching Some

Shooting Skills for Basketball Beginners. Annals of

Applied Sport Science, 11(2):3.

Ferioli, D., Conte, D., Rucco, D., Alcaraz, P. E., Vaquera,

A., Romagnoli, M., & Rampinini, E.(2023a) Physical

Demands of Elite Male and Female 3 x 3 International

Basketball Matches. Journal of Strength and

Conditioning Research, 37(4): E289-E296.

Ferioli, D., Conte, D., Scanlan, A. T. T., & Vaquera,

A.(2023b) Technical-Tactical Demands of 3 x 3

International Basketball Games According to Game

Outcome, Player Sex, and Competition Phase. Journal

of Strength and Conditioning Research, 37(2): 403-412.

Ferioli, D., Rampinini, E., Conte, D., Rucco, D.,

Romagnoli, M., & Scanlan, A.(2023c) Physical

demands during 3? 3 international male and female

basketball games are partially impacted by competition

phase but not game outcome. Biology of Sport, 40(2):

377-387.

Goldschmied, N., Raphaeli, M., & Morgulev, E.(2023)

"Icing the shooter" in basketball: The unintended

consequences of time-out management when the game

is on the line. Psychology of Sport and Exercise,

68(3):2.

Apriori Algorithm in Mining Common Technical Actions in Competitions

423

Gou, Q., & Li, S.(2023) Study on the correlation between

basketball players' multiple-object tracking ability and

sports decision-making. Plos One, 18(4):2.

Horvat, T., Job, J., Logozar, R., & Livada, C.(2023) A Data-

Driven Machine Learning Algorithm for Predicting the

Outcomes of NBA Games. Symmetry-Basel, 15(4):78.

Ibanez, S. J., Pinar, M. I., Garcia, D., & Mancha-Triguero,

D.(2023) Physical Fitness as a Predictor of

Performance during Competition in Professional

Women's Basketball Players. International Journal of

Environmental Research and Public Health, 20(2):98.

Jane, W.-J., Chen, S. T., & Su, Y. J.(2023) Contestant

Heterogeneity and Hack-a-Shaq Strategy in Team

Efforts in Professional Basketball Games. International

Journal of Sport Finance, 18(1): 3-18.

Jin, P., Ge, Z., & Fan, T.(2023) Research on visual search

behaviors of basketball players at different levels of

sports expertise. Scientific Reports, 13(1):89.

Koba, T. H., Nagel, M. S., Watanabe, N. M., Yan, G.,

Southall, R. M., & Kidd, V. K.(2023) An Exploration

of Professional US-Based Basketball Players

Competing in Turkey. Journal of Global Sport

Management, 8(1): 161-182.

INCOFT 2025 - International Conference on Futuristic Technology

424