CN112070411A - Method for evaluating adaptation degree of new players and teams in basketball tournament - Google Patents
Method for evaluating adaptation degree of new players and teams in basketball tournament Download PDFInfo
- Publication number
- CN112070411A CN112070411A CN202010965033.5A CN202010965033A CN112070411A CN 112070411 A CN112070411 A CN 112070411A CN 202010965033 A CN202010965033 A CN 202010965033A CN 112070411 A CN112070411 A CN 112070411A
- Authority
- CN
- China
- Prior art keywords
- player
- new
- players
- new player
- team
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000006978 adaptation Effects 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000003062 neural network model Methods 0.000 claims abstract description 17
- 238000007477 logistic regression Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 6
- 238000012216 screening Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063112—Skill-based matching of a person or a group to a task
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method for evaluating the adaptation degree of a new player and a team in a basketball tournament, which comprises the following steps: s10 obtaining configuration parameters S1 of a new player a, setting the number m of players in a team of the same category as the new player a, and when m belongs to [2,5], S1 is 0.3, otherwise, S1 is 0; s20 obtains a match parameter S2 of the new player a, classifies the new player a using a neural network model, and S2 is 0.4 when the type of the new player a is a good match, S2 is 0.2 when the type of the player is a good match, and S2 is 0 when the type of the player is a bad match; s30, obtaining a competition field performance parameter S3, wherein the stable performance output is S3-0.3, otherwise S3-0; and a higher value of S40ST indicates a higher degree of adaptation of the new player to the team, where ST is S1+ S2+ S3. According to the method for evaluating the adaptation degree of the new basketball players and the teams in the basketball tournament, the adaptation parameter ST is used for evaluating the adaptation degree of the new basketball players and the teams more objectively, accurately, truly and practically than artificially evaluating, and the new basketball players with higher adaptation degree are selected for the teams.
Description
Technical Field
The invention relates to the technical field of player match selection, in particular to a method for evaluating the adaptation degree of a new player and a team in a basketball tournament.
Background
Currently, player screening is generally performed from several aspects:
(1) by experience screening, in the current basketball professional league, the method for evaluating the new players by the team is more based on the judgment of the experiences of the coach group and the team management layer, abundant player technical statistics provided in the professional league are not fully utilized, the situation that the new players are difficult to adapt to the team due to the fact that the technical style is not consistent with the team after entering the team often occurs, the significance behind the past technical statistical information of the players needs to be manually intervened and analyzed, the internal technical characteristics of more players are found from the back of data, and the risk that the new players cannot adapt to the team is reduced.
(2) Evaluation of a new player, a coach in a current basketball professional league usually evaluates the technical style of the player by using traditional technical statistics such as scoring, backboard and attack assistance, and the traditional technical statistics are greatly influenced by factors such as the time of the player on the scene and the like, so that the technical style of one player and the real efficiency in a match cannot be completely reflected, and a coach group has some deviation when evaluating the adaptation degree of the new player and a team.
(3) Management of new players, when the adaptability of the new players and teams is evaluated in teams in the current basketball professional competition, the performance of the new players in the past in a playing field is more concerned, and comprehensive evaluation is not carried out on aspects of similarities and differences of technical styles of the new players and other players of the teams, the matching degree of the new players and the styles of core players and the like, so that the past excellent playing field performance of the new players is not continued in the new teams.
(4) New player skill judgment, it is common for trainers in teams in current basketball professional tournaments to want a player with a similar technical style to an ideal player in some trainers when picking a new player, and it is difficult to accurately judge whether a player is similar to the ideal player that the trainer wants. There is a need for a method to more specifically determine whether a player has certain technical styles that the coach wants.
Based on the above points, a more objective and more accurate method for screening new players and team adaptation degree is needed.
Disclosure of Invention
In order to solve the problems, the invention provides a method for evaluating the adaptation degree of a new player and a team in a basketball tournament, which evaluates the adaptation degree of the new player and the team by using an adaptation parameter ST more objectively, accurately, truly and practically than artificially evaluating, and selects the new player with higher adaptation degree for the team.
In order to achieve the above purpose, the invention adopts a technical scheme that:
a method for evaluating the adaptation degree of a new player and a team in a basketball tournament comprises the following steps: s10 obtaining configuration parameters S1 of a new player a, setting the number m of players in a team of the same category as the new player a, and when m belongs to [2,5], S1 is 0.3, otherwise, S1 is 0; s20 obtains a match parameter S2 of the new player a, manually classifies all players into three types of good match, general match, and non-match, and classifies the new player a using a neural network model, where S2 is 0.4 when the type of the new player a is good match, S2 is 0.2 when the type of the player is general match, and S2 is 0 when the type of the player is non-match; s30, obtaining a playing field performance parameter S3, predicting the performance of each new player after the new player joins the team by using a logistic regression classifier according to the playing field performance of each new player before replacing the team, wherein the stable output of the performance is S3-0.3, otherwise, S3-0; and S40 obtaining a new player and team adaptation parameter ST, wherein the higher ST value indicates the higher adaptation degree of the new player to the team, and the ST is S1+ S2+ S3.
Further, the S10 includes the following steps: s11, establishing a technical index database of players in the basketball tournament; s12, clustering the main players of each field in the basketball tournament according to the technical index database by using a K-means algorithm, and dividing all players into K categories, wherein K is a multiple of 5; and S13, setting the number m of the existing players in the Ki-th category in the team as the new player a in the Ki-th category, wherein when m belongs to [2,5], S1 is 0.3, otherwise S1 is 0, wherein i is a positive integer of [1, K ], and the new player a is any candidate new player.
Further, the player technical index database includes an attack back body single hit rate, a shot making rule rate, a time of departure, and a control backboard rate for each player.
Further, the S20 includes the following steps: s21, manually classifying all the players into three types of very-conforming, general-conforming and non-conforming, and converting the technical index data of the classified main players into standard characteristic data which can be recognized by a machine; s22, constructing a neural network model, wherein the vector dimension of an input layer is m x 1, m is the number of technical index items of the player, the vector dimension of an output layer is 3 x 1, 2-3 hidden layers are set, and the number of neurons in the hidden layers is 10-256; s23, training a neural network model, training and testing the neural network model by using the standard characteristic data, and adjusting the architecture and parameters of the neural network; and S24 classifying the new player a using the trained neural network model, S2 being 0.4 when the type of the new player a is in good agreement, S2 being 0.2 when the type of the player is in good agreement, and S2 being 0 when the type of the player is out of agreement.
Further, the main player is a player with the departure time of more than 20 min.
Further, in the step S30, the logistic regression classifier and sigmoid function are used to convert the technical index data of the new player a into a value ranging from 0 to 1, and when the value is less than 0.5, S3 is 0.3, otherwise S3 is 0.
Compared with the prior art, the technical scheme of the invention has the following advantages:
(1) the invention relates to a method for evaluating the adaptation degree of a new player and a team in a basketball tournament, which comprises the steps of processing technical index data of players through a K-means algorithm, a neural network model and a logistic regression model to obtain configuration parameters S1, conformity parameters S2 and a playing field performance parameter S3 of any new player, combining S1, S2 and S3 to obtain an adaptation parameter ST of the new player and the team, evaluating the adaptation degree of the new player and the team by using the adaptation parameter ST more objectively, accurately, truly, practically and practically than artificially evaluating, and selecting the new player with higher adaptation degree for the team.
(2) The method for evaluating the adaptation degree of the new basketball team and the new basketball team in the basketball tournament provided by the invention changes subjective judgment considered by a coach and the like into data statistical information which can reflect the real technical characteristics of the basketball team through data mining and analysis, and provides scientific judgment for the coach from the aspects of team style adaptation degree, requirements and preferences of the coach on the basketball team, prediction of performance of the basketball team after the basketball team enters the new basketball team and the like.
(3) According to the method for evaluating the adaptation degree of the new players and the team in the basketball tournament, the technical styles of the players are clustered, so that the situation that the team has too many or too few players of the same type is reduced, the possibility that the styles of the new players and the team are not consistent is reduced, and the possibility that the competition in the same position in the team is too violent is also reduced.
(4) The method for evaluating the adaptation degree of the new players and the teams in the basketball tournament provided by the invention has the advantages that the analyzed and sorted technical index data is utilized to optimize the logistic regression model, whether the performance of the players entering the new teams in the basketball tournament is stable or not is analyzed, the possible performance conditions of the players entering the new teams are evaluated, and the method is further optimized.
Drawings
The technical solution and the advantages of the present invention will be apparent from the following detailed description of the embodiments of the present invention with reference to the accompanying drawings.
FIG. 1 is a flowchart of a method for evaluating the fitness of a new player and team in a basketball tournament according to one embodiment of the invention;
fig. 2 is a simplified flowchart of a method for evaluating the fitness of a new player and a team in a basketball tournament according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the method for evaluating the adaptability of the new player of the basketball tournament to the team, as shown in fig. 1-2, S10 obtains a configuration parameter S1 of the new player a, sets the number m of players in the team in the same category as the new player a, and when m belongs to [2,5], S1 is 0.3, otherwise, S1 is 0. S20 obtains a match parameter S2 of the new player a, manually classifies all players into three types of good match, general match, and non-match, and classifies the new player a using a neural network model, S2 being 0.4 when the type of the new player a is good match, S2 being 0.2 when the type of the player is general match, and S2 being 0 when the type of the player is non-match. S30 obtains the playing field performance parameters S3, the performance of each new player after the new player joins the team is predicted by a logistic regression classifier according to the playing field performance of the new player in the previous year of replacing the team, the stable output of the performance is S3-0.3, otherwise, S3-0. And S40 obtaining a new player and team adaptation parameter ST, wherein the higher ST value indicates the higher adaptation degree of the new player to the team, and the ST is S1+ S2+ S3.
The S10 includes the following steps: s11, establishing a database of technical indexes of players in the basketball tournament. The player technical index database comprises the attack back body single-shot rate, the shooting rule making rate, the departure time, the control backboard rate and the like of each player.
S12 clustering the main players of each court in the basketball tournament according to the technical index database by using a K-means algorithm, and dividing all players into K categories, wherein K is a multiple of 5. Since in basketball games players are typically divided into 5 different positions, it is appropriate to locate the value of K by a multiple of 5. First, K initial points are randomly determined as centroids (not points in the data), and then each point in the data set is assigned to a cluster, specifically, the closest centroid is found for each point and assigned to the cluster to which the centroid corresponds. The main player is a player with the time of leaving more than 20 min.
And S13, setting the number m of the existing players in the Ki-th category in the team as the new player a in the Ki-th category, wherein when m belongs to [2,5], S1 is 0.3, otherwise S1 is 0, wherein i is a positive integer of [1, K ], and the new player a is any candidate new player. In general, when too many players of the same type are present in a team, the tactical flexibility of the team is reduced, and the team is likely to compete maliciously. When the number of players of the same type is too small, the tactics of the team can lack integrity and cannot form a unique style. Therefore, the number of the new players and the number of the players in the same category of the team need to be in a reasonable interval, and the new players can be guaranteed to have good use degree in the team. A reasonable interval of the number m of the existing players in the same category as a new player in a team is set to be 2-5 (closed interval), a value S1 is defined, when the number of players is in the interval, S1 is 0.3, otherwise, the number of players is 0S 1.
The S20 includes the following steps: s21, manually classifying all the players into three types of perfect-fit, general-fit and non-fit, and converting the technical index data of the classified main players into standard characteristic data which can be recognized by a machine, so that the machine recognition is facilitated.
S22 a neural network model is built, the vector dimension of the input layer is m x 1, m is the number of technical index items of the player, the vector dimension of the output layer is 3 x 1, 2-3 hidden layers are set, and the number of neurons in the hidden layers is 10-256. If the number of technical indicators contained in the database of selected player technical indicators is 16, the vector dimension of the input layer is 16 x 1. The players are classified into three categories, so the vector dimension of the output layer is 3 x 1.
S23, training a neural network model, training and testing the neural network model by using the standard characteristic data, and adjusting the architecture and parameters of the neural network.
S24 classifies new player a using the trained neural network model, S2 being 0.4 when the type of new player a is in good agreement, S2 being 0.2 when the type of player is in good agreement, and S2 being 0 when the type of player is out of agreement.
In the step S30, the logistic regression classifier and sigmoid function are used to convert the technical index data of the new player a into a value ranging from 0 to 1, and when the value is less than 0.5, S3 is 0.3, otherwise S3 is 0.
In the basketball tournament, there are many players who have stable performance after entering a new team, and there are also players who have rapid downward sliding performance after entering the new team. The data statistics of the players, which are changed for the previous year of the team, are sorted, and the players are marked according to whether the performance of the players slips down after the players are added to a new team. And predicting the performance (stability or glide) of the new player after the new player joins the team by using the technical index data in the technical index database by using a logistic regression classifier, wherein the performance is stable to be 0 class and the performance glide is 1 class. The method comprises the following specific steps:
by means of the logistic regression classifier, a regression coefficient can be multiplied on each piece of digitized standard feature data, all result values are added, the sum is substituted into a Sigmoid function, and a value ranging from 0 to 1 is obtained. Any data greater than 0.5 is classified as class 1, and any data less than 0.5 is classified as class 0.
The formula is as follows:
z＝w0x0+w1x1+w2x2+……+wnxn
wherein z is the input of the sigmoid function, w is the weight parameter, x is the value of a feature, n is the number of the feature and the weight parameter, and σ is the sigmoid function.
And (4) parameter learning, namely training a logistic regression classifier by using the standard feature data marked before. And using the cross entropy as a loss function, and performing parameter learning by using a gradient descent method. And (5) carrying out classification prediction on the technical index data of the new player a by using a trained logistic regression classifier, and recording a prediction result. If the prediction result is 0 type, the score of S3 is 0.3; when the prediction result is class 1, the value of S3 is 0.
The above description is only an exemplary embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes that are transformed by the content of the present specification and the attached drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (6)
1. A method for evaluating the adaptation degree of a new player and a team in a basketball tournament is characterized by comprising the following steps:
s10 obtaining configuration parameters S1 of a new player a, setting the number m of players in a team of the same category as the new player a, and when m belongs to [2,5], S1 is 0.3, otherwise, S1 is 0;
s20 obtains a match parameter S2 of the new player a, manually classifies all players into three types of good match, general match, and non-match, and classifies the new player a using a neural network model, where S2 is 0.4 when the type of the new player a is good match, S2 is 0.2 when the type of the player is general match, and S2 is 0 when the type of the player is non-match;
s30, obtaining a playing field performance parameter S3, predicting the performance of each new player after the new player joins the team by using a logistic regression classifier according to the playing field performance of each new player before replacing the team, wherein the stable output of the performance is S3-0.3, otherwise, S3-0; and
s40 obtains a new player and team adaptation parameter ST, where a higher ST value indicates a higher degree of adaptation of the new player to the team, where ST is S1+ S2+ S3.
2. The method of claim 1, wherein the step of S10 comprises the steps of:
s11, establishing a technical index database of players in the basketball tournament;
s12, clustering the main players of each field in the basketball tournament according to the technical index database by using a K-means algorithm, and dividing all players into K categories, wherein K is a multiple of 5;
and S13, setting the number m of the existing players in the Ki-th category in the team as the new player a in the Ki-th category, wherein when m belongs to [2,5], S1 is 0.3, otherwise S1 is 0, wherein i is a positive integer of [1, K ], and the new player a is any candidate new player.
3. The method of claim 2 wherein the player technical index database comprises a single shot rate of attack, a shooting build rate, a time of departure, and a control backboard rate for each player.
4. The method of claim 1, wherein the step of S20 comprises the steps of:
s21, manually classifying all the players into three types of very-conforming, general-conforming and non-conforming, and converting the technical index data of the classified main players into standard characteristic data which can be recognized by a machine;
s22, constructing a neural network model, wherein the vector dimension of an input layer is m x 1, m is the number of technical index items of the player, the vector dimension of an output layer is 3 x 1, 2-3 hidden layers are set, and the number of neurons in the hidden layers is 10-256;
s23, training a neural network model, training and testing the neural network model by using the standard characteristic data, and adjusting the architecture and parameters of the neural network; and
s24 classifies new player a using the trained neural network model, S2 being 0.4 when the type of new player a is in good agreement, S2 being 0.2 when the type of player is in good agreement, and S2 being 0 when the type of player is out of agreement.
5. The method of claim 4 wherein the lead player is a player with a time to field greater than 20 min.
6. The method as claimed in claim 5, wherein the step of S30 uses logistic regression classifier and sigmoid function to convert the technical index data of the new player a to a value ranging from 0 to 1, when the value is less than 0.5, S3 is 0.3, otherwise S3 is 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010965033.5A CN112070411A (en) | 2020-09-15 | 2020-09-15 | Method for evaluating adaptation degree of new players and teams in basketball tournament |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010965033.5A CN112070411A (en) | 2020-09-15 | 2020-09-15 | Method for evaluating adaptation degree of new players and teams in basketball tournament |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112070411A true CN112070411A (en) | 2020-12-11 |
Family
ID=73695233
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010965033.5A Pending CN112070411A (en) | 2020-09-15 | 2020-09-15 | Method for evaluating adaptation degree of new players and teams in basketball tournament |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112070411A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220374475A1 (en) * | 2021-05-18 | 2022-11-24 | Stats Llc | System and Method for Predicting Future Player Performance in Sport |
-
2020
- 2020-09-15 CN CN202010965033.5A patent/CN112070411A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220374475A1 (en) * | 2021-05-18 | 2022-11-24 | Stats Llc | System and Method for Predicting Future Player Performance in Sport |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Baker et al. | Defining expertise: A taxonomy for researchers in skill acquisition and expertise | |
| Reed et al. | Development and application of computer-based prediction methods | |
| Gu et al. | Expert system for ice hockey game prediction: Data mining with human judgment | |
| Warnakulasuriya et al. | Discovering methods of scoring in soccer using tracking data | |
| Jain et al. | Sports result prediction using data mining techniques in comparison with base line model | |
| Pugsee et al. | Football match result prediction using the random forest classifier | |
| CN110222723A (en) | A kind of starting prediction technique of football match based on mixed model | |
| Somaskandhan et al. | Identifying the optimal set of attributes that impose high impact on the end results of a cricket match using machine learning | |
| CN112070411A (en) | Method for evaluating adaptation degree of new players and teams in basketball tournament | |
| Sinha | Application of machine learning in cricket and Predictive Analytics of IPL 2020 | |
| Das et al. | Adoption of a ranking based indexing method for the cricket teams | |
| Kim et al. | March Madness prediction: Different machine learning approaches with non‐box score statistics | |
| Anwar et al. | Artificial intelligence-driven approach to identify and recommend the winner in a tied event in sports surveillance | |
| Su et al. | Basketball players' score prediction using artificial intelligence technology via the Internet of Things | |
| CN110297886A (en) | OJ topic classifier construction method and topic analogy method based on short text | |
| Haq et al. | Machine Learning Techniques for Result Prediction of One Day International (ODI) Cricket Match | |
| Ghosh et al. | Indian premier league player selection model based on Indian domestic league performance | |
| Bose et al. | Unsupervised learning based evaluation of player performances | |
| Zeng et al. | A Machine Learning Model to Predict Player's Positions based on Performance. | |
| Srinivasan | A Social Network Analysis of Football-Evaluating Player and Team Performance | |
| Radhika et al. | Premier League table prediction using machine learning algorithms | |
| Bhawkar et al. | Predicting the winner of indian premier league match: A comparative study | |
| CN114832386B (en) | Game user intelligent management system based on big data analysis | |
| Al Asad et al. | Impact of a Batter in ODI Cricket Implementing Regression Models from Match Commentary | |
| Ju et al. | Research on the Characteristics of Wordle Mini-Game Based on GA-BP Neural Network and K-Means Clustering Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201211 |
|
| RJ01 | Rejection of invention patent application after publication |