Ninth International Joint Colloquiums on Computer Electronic Electrical Mechanical and Civil-CEMC2024

AI-Driven Analytics for Batsman Performance Index in T20I

Cricket: A New Era of Evaluation
Dr Anil V Turukmane
School of Computer Science and Engineering
VIT-AP University, Vijayawada, AP, India
Email: [email protected]

Mr. Pendyala Sri Pranav

Student, School of Computer Science and Engineering
VIT-AP University, Vijayawada, AP, India Email:
[email protected]

Mr. Chintapenta Sai Rahul Bharadwaj

Student, School of Computer Science and Engineering VIT-AP
University, Vijayawada, AP, India
Email: [email protected]

Mr. Aryan A Shinde

Student, School of Computer Science and Engineering
VIT-AP University, Vijayawada, AP, India
Email: [email protected]

Mr. Digvijay T Patil

Student, School of Computer Science and Engineering
VIT-AP University, Vijayawada, AP, India
Email: [email protected]

Abstract—Cricket is more than just a sport in India; it is a cultural phenomenon that connects
millions of fans. With a global audience exceeding 2.5 billion, cricket is one of the most beloved
sports worldwide. The rapid evolution of technology, particularly through Artificial Intelligence (AI)
and Machine Learning (ML), has transformed the sports analytics industry, primarily cricket
analysis and analytics, especially in the T20 format—a dynamic version of the game requiring rapid
strategic decisions and standout performances. This study proposes a novel Batsman Performance
Index (BPI) specifically for T20 Internationals (T20Is). Utilizing cutting-edge analytics and data
training of intelligence systems which help in prescribing or predictive analysis, the BPI offers a
detailed evaluation of batsmen based on performance metrics such as strike efficiency, scoring
patterns, and match impact. This innovative index not only supports strategic decision-making and
player selection but also enhances fan engagement by forecasting high-impact performances. By
harnessing insights into player behaviour and performance trends, the BPI provides valuable tools
for teams, broadcasters, and sponsors to create more engaging and strategic cricket experiences in
the digital era.
Keywords: Strategic Performance Metrics, Prescribing/Predictive Player Analytics, Impact
Assessment, Scoring Patterns, Cricket Forecasting.
I. INTRODUCTION
Cricket is more than just a sport in India; it is a cultural phenomenon that unites millions of fans across the country. The
passion for cricket extends beyond the boundaries of the pitch, with fans deeply invested in every match, player, and strategy.
Countries like Australia, England, South Africa, and Pakistan, along with the Indian subcontinent, have strong cricket
traditions, contributing to the sport’s rich history and ever-growing popularity. In recent years, the rise of Artificial Intelligence
(AI) and Machine Learning (ML) leveraging data analytics has
revolutionized how cricket is played, predicted, analysed, and consumed. Teams and selectors no longer rely solely on
intuition and experience to choose players; instead, they delve into detailed performance metrics to make informed
decisions. This shift is equally evident in the burgeoning fantasy sports industry, where millions of users create virtual teams
based on real players’ statistics, vying for the best possible lineup. The demand for accurate performance analysis has also
fueled the growth of comparative studies, where players are assessed against each other based on a variety of metrics, from
strike rates to consistency under pressure. T20 cricket, in particular, has emerged as a game-changer, transforming the sport
into a more fast-paced and viewer-friendly spectacle. The shorter format not only enhances the watchability of the game but
also drives significant revenue streams through marketing, gaming, and youth talent identification. The explosive popularity
of T20 cricket has reshaped the sport’s commercial landscape, with franchises and leagues capitalizing on its appeal to
attract younger audiences and new fans globally. The T20 format has revolutionized talent identification by showcasing
young players’ performance under pressure and strategic thinking. Its fast pace demands resilience and adaptability, offering
key insights into players’ potential. Our paper introduces the Batsman Performance Index (BPI), a powerful tool for analysing
T20 performance metrics, thereby refining talent evaluation with greater accuracy and depth. This paper also explores the
critical link between player performance and fan engagement in modern cricket. With the rise of digital platforms,
understanding fan behaviour has become essential for teams, broadcasters, and sponsors as understanding and leveraging
fan behaviour can lead to more effective marketing strategies, enhanced viewer experiences, and greater overall
engagement in the digital age.

II. LITERATURE REVIEW: COMPARISON WITH EXISTING METRICS IN T20 CRICKET

A. Introduction to T20 Cricket and Performance Evaluation
T20 cricket, a format that demands rapid adaptability and high-pressure performances, has revolutionized the evaluation of
batsmen’s contributions on the field. Traditional metrics like Batting Average (AVG) and Strike Rate (SR) have been pivotal in
assessing batsman performance. However, these metrics often fall short of capturing the full scope of a player’s impact,
particularly in the dynamic and situational nature of T20 cricket, where a player’s contribution can vary significantly based on
the context.

B. Traditional and Advanced Metrics

While Strike Rate and Average’s remain important, they do not provide a complete picture of a batsman’s effectiveness in
T20 cricket. To address this, the Batsman Performance Index (BPI) integrates both traditional and advanced metrics :
• Strike Rate (SR): Measures the speed at which a batsman scores runs, crucial for maintaining the tempo in T20 cricket.

• Boundary Percentage (Boundary%): Indicates a batsman’s ability to score boundaries, reflecting their dominance over
bowlers.

• Batting Average (AVG): Provides an overall measure of consistency, showing how often a batsman scores significant runs.

• Fifties and Hundreds: Represents the frequency of significant contributions, essential for winning matches.
• Not Outs (NO): Highlights the number of times a batsman remains unbeaten, demonstrating their ability to stay at the
crease and contribute to the team’s total in crucial moments.
Michael Hussey [2] introduced a simple index to evaluate a batsman’s performance in Twenty20 cricket, referred to as the
Hussey Index or Hussey’s Batting Score. The index is calculated using the formula: Hussey Index = PBSR+PBA Here:
• PBSR represents the Player Batting Strike Rate.

2
• PBA stands for the Player Batting Average.
Hussey suggests that a score exceeding 150 on this index indicates strong performance. This measure effectively integrates
two key aspects of batting: the player’s ability to score rapidly (strike rate) and consistently (average).
Mr. Deep and Mr. Patvardhan from the IITM introduced the DPPI (Deep Player Performance Index), which is calculated using
the standard formula:

where:
• AVG is the Player Batting Average.
• STR is the Player Batting Strike Rate.
[1]
While the Hussey Index and DPPI provide useful insights by combining Strike Rate and Batting Average, they tend to either
oversimplify or overcomplicate the analysis, making it challenging to accurately compare or rank players. The Hussey Index,
though straightforward, may not capture the full spectrum of a batsman’s contributions, while the DPPI, by integrating Strike
Rate and Average, can sometimes mask other critical performance factors. To address these limitations, we have introduced
the Batsman Performance Index (BPI). The BPI is designed to be a more comprehensive yet straightforward metric,
incorporating a broader range of key performance indicators (KPIs) that are crucial for evaluating batsmen in T20
Internationals. By balancing traditional metrics with advanced ones, the BPI offers a clearer and more accurate assessment
of a player’s effectiveness in the fast-paced T20 format.

The Most Valuable Player Index (MVPI) evaluates a batsman’s overall contribution by aggregating batting, bowling, and
fielding performances into a single score. For batsmen, the MVPI formula is:
MVPI for Batsmen = Batting Points + Fielding Points (4)
where Batting Points typically include runs scored, boundaries, and strike rate, while Fielding Points account for fielding
contributions like catches and run-outs. However, the MVPI’s broad approach can sometimes obscure critical batting metrics
essential for formats like T20 cricket. For instance, while the MVPI accounts for runs and boundaries, it may not adequately
emphasize the importance of a high Strike Rate or Boundary Percentage, which are crucial for evaluating a batsman’s impact
in shorter formats.
To address these limitations, we introduce the Batsman Performance Index (BPI), focusing exclusively on key batting metrics
such as Strike Rate, Boundary Percentage, and Batting Average. This specialized approach offers a clearer picture of a
batsman’s effectiveness in T20 Internationals, highlighting those who excel under pressure and providing more precise
insights for evaluation and comparison. Unlike the MVPI, which aggregates batting, bowling, and fielding contributions, the
BPI emphasizes the batting aspects most relevant to T20 success. By concentrating on these critical metrics, the BPI ensures
a targeted assessment of top-performing batsmen and facilitates more informed decision-making for team selection and
strategy.

III. PROPOSED MODEL AND METHODOLOGY

The proposed model, the Batsman Performance Index (BPI), is designed to provide a comprehensive evaluation of T20I
players by going beyond traditional performance metrics. Unlike conventional metrics that focus solely on averages and
strike rates, the BPI integrates additional performance indicators to offer a more nuanced assessment of a player’s
contributions on the field. This model aims to address the limitations of traditional methods by incorporating elements like
boundary-hitting efficiency, strike rate, not outs, hundreds and fifties, boundary percentage, and role-specific contributions,
providing a holistic view of a player’s impact on the game.

A. Data Extraction
The foundation of the BPI model is rooted in a rigorous data collection process. The primary dataset was sourced from
Cricmetric, a well-regarded platform for cricket statistics. This dataset was meticulously curated to include variables essential
for assessing a batsman’s performance in T20I cricket. The key columns extracted from the dataset include:
• Year: Captures the year each match was played, allowing for an analysis of performance trends over time.
• Runs: Represents the total runs scored by the batsman, directly indicating their contribution to the team’s score.
• Batting Average: This metric, calculated as the total runs divided by the number of times a batsman has been dismissed,
reflects the batsman’s ability to score consistently.
• Strike Rate: Shows the rate at which a batsman scores runs per 100 balls, a critical measure of their scoring efficiency in
T20I cricket.
• 50s and 100s: Records the number of half-centuries and centuries scored by the batsman, indicating their ability to convert
starts into significant contributions.
• 4s and 6s: Tracks the number of boundaries (fours and sixes) hit by the batsman, offering insights into their aggressive play
and boundary-hitting capability.

3
• Boundary Percentage: Calculates the percentage of runs scored through boundaries, giving a glimpse into a batsman’s
aggressive intent and shot selection.
This comprehensive dataset enables the BPI model to capture a detailed and accurate picture of a batsman’s performance,
evaluating not just the volume of runs but also the efficiency, consistency, and impact of their contributions.

B. Data Validation

To ensure the accuracy and reliability of the data, a thorough validation process was undertaken. The initial dataset from
Cricmetric was cross-referenced with ESPN Cricinfo, a globally trusted source for cricket statistics. This step was crucial for
verifying the consistency of the data and ensuring alignment with widely recognized sources. During the validation process,
key performance indicators such as runs, batting average, strike rate, and boundary counts were meticulously compared
between Cricmetric and ESPN Cricinfo. Any discrepancies identified were resolved through further investigation, ensuring
that the final dataset used for BPI calculations was both accurate and reliable.

C. Data Verification
As a final measure of quality assurance, the dataset underwent a verification process using CricSheets, known for providing
detailed ball-by-ball data for cricket matches. Cric Sheets data was used to cross-check specific match details, such as runs
scored, balls faced, and boundary hits, ensuring the integrity of the dataset. The verification process also involved checking
for completeness, ensuring that all relevant matches and performances were included in the dataset. Any missing or
incomplete data points were addressed by sourcing the necessary information from alternative reliable databases.

D. Integration of Enhanced Metrics

With a validated and verified dataset in place, advanced metrics were integrated using Kaggle’s extensive cricket datasets.
These enhanced metrics provided additional insights into player performance, capturing elements that traditional statistics
might overlook. For instance, detailed analysis of boundary-hitting efficiency was made possible by considering the
frequency of boundaries relative to balls faced in different match situations. Integrating these advanced metrics into the BPI
model enhances the analysis, allowing for a more nuanced and sophisticated evaluation of players. By combining traditional
performance data with these enriched indicators, the BPI model offers a comprehensive tool for assessing batsmen in T20I
cricket.

E. Calculation of the Batsman Performance Index (BPI)

The BPI is calculated by combining these metrics into a single, comprehensive score. Each metric is normalized to account for
differences in playing conditions and eras and then weighted based on its importance in T20 cricket. For example, SR and
Boundary% might carry more weight due to their direct influence on scoring rates, while AVG and Boundary% provide
additional context to a batsman’s consistency and ability to sustain innings. To determine the weights for the Batsman
Performance Index (BPI), we employed a comprehensive approach combining statistical analysis, machine learning models,
and expert consultation. We analyzed extensive T20I data using techniques such as linear regression to assess the impact of
each metric. We analysed interviews with cricket experts, including Ravichandran Ashwin, consulted with cricket analysts,
and reviewed insights from Twitter and LinkedIn posts by various cricket analysts. This multifaceted approach ensured that
the weights accurately reflect the significance of metrics like Strike Rate, Boundary Percentage, and Batting Average in
evaluating batsman performance.

4
F. The standard formula for calculating the Batsman Performance Index (BPI) is given by:

G. Weighted Formula

The weighted formula for calculating the Batsman Performance Index (BPI), considering the importance of each metric, is
given by:

This formula allows for a balanced and fair comparison by normalizing and weighting each metric according to its relevance
in the T20 format.

H. Validation Across T20 Internationals (T20Is)

The Batsman Performance Index (BPI) was rigorously validated using a comprehensive dataset from T20 Internationals
(T20Is). It consistently demonstrated superior performance compared to traditional metrics such as Batting Average and
Strike Rate, providing more precise and insightful evaluations of player performance. The BPI effectively integrates essential
performance metrics, including boundary hitting, strike rotation, and overall consistency, offering a detailed assessment that
enhances player comparisons.

5
I. Era-Based Comparisons

Direct comparisons between batsmen from different eras can be problematic due to evolving conditions, competition, and
playing styles. To address this issue, we introduce the Normalized Batsman Performance Index (BPI). This concept adjusts the
BPI to account for the unique conditions and competitiveness of each era, enabling more equitable comparisons across
different time periods. By normalizing performances based on era-specific factors, the Normalized BPI provides a more
accurate and fair assessment of batsmen from various decades. This approach ensures that historical comparisons are as
accurate as possible, accounting for changes in the game over time.

J. Normalized BPI Calculation

The formula for Normalized Batsman Performance Index (BPI) is given by :

K. Calculating Era’s Average Metrics

To calculate the metrics for a specific era, which is defined as a decade (10 years)
• Era’s Average (Avg):

where only players with a batting average of at least 25 are included.

• Era’s Strike Rate (SR):

where only players with a strike rate of at least 60 are included.

• Era’s Hundreds (100s):

where only players who have faced at least 1000 balls are included

IV. RESULTS AND DISCUSSION

A Batsmen Performance Index (BPI) Analysis

1. Model Validation and Comparative Performance:
Validation Across T20Is: The BPI was validated using a diverse dataset from T20 Internationals (T20Is). The BPI consistently
outperformed traditional metrics such as Batting Average and Strike Rate in providing accurate and insightful evaluations of
player performance.
Era Comparison: Comparing batsmen across different eras is challenging due to evolving conditions, competition, and
playing styles. To address this, a Normalised Batsman Performance Index (BPI) was introduced. This metric adjusts a player’s
performance based on how they stood out in their own era, allowing for fairer comparisons across time.

Example of Normalised BPI Calculation:

Virat Kohli:

6
Viv Richards:

The Normalised BPI shows that Kohli’s score is 335 points higher than Richards’, highlighting his dominance in his era.

2) Emerging Players: The BPI identifies promising talents who may not yet have the highest traditional statistics but
exhibit substantial potential. For instance, players like Nicholas Pooran and Rassie van der Dussen demonstrate high BPIs,
indicating their potential to excel as they gain more experience and continue refining their skills.

3) Consistency Over Time: BPI also emphasizes consistency, which is crucial in T20 cricket. Players who maintain high
BPI scores across matches and tournaments are shown to be more reliable and valuable to their teams.

B. Fan Engagement Insights

1) Engagement Drivers: Player Performance: Individual performances, especially in moments that change the course
of the game, are primary drivers of fan engagement. Match Context: Engagement intensifies during critical match contexts,
such as knockout stages or traditional rivalries, where high-BPI players are more likely to influence the outcome.
2) Demographics and Engagement Patterns: Youth Engagement: Younger fans, particularly those aged 18-30, are
drawn to players with high BPIs on digital platforms like Instagram, Twitter, and YouTube. These platforms allow fans to
engage in real time discussions and share highlights, with high-BPI players often becoming the focal point.
Example: Virat Kohli’s incredible performance against Pakistan in the 2022 T20 World Cup led to a surge in social media
activity, demonstrating the strong appeal of high-BPI players in the digital age.
Geographical Insights: South Asian countries show the highest levels of interest in cricket content, with regional players like
Virat Kohli and Babar Azam driving viewership and social media discussions.
To demonstrate that the Batsman Performance Index (BPI) is a subset of fan engagement, we can establish a mathematical
relationship between these metrics.

Let:
• BPI represent the Batsman Performance Index.
• FE represent Fan Engagement, which includes various metrics such as fan interaction, social media activity, and
merchandise sales.
We can express the BPI as a subset of fan engagement metrics as follows:
BPI FE
To illustrate this, we decompose the Fan Engagement (FE) into components that BPI directly influences. Let:
• Interactions be the total fan interactions.
• Social Media Activity be the engagement on social media platforms.
• Merchandise Sales be the sales of player-related merchandise.
We express fan engagement (FE) as a combination of these components:

FE =f(Interactions ,Social Media Activity, Merchandise Sales) where f is a

function that aggregates these metrics.

The BPI, which is based on performance metrics like strike rate, average, and boundary percentage, influences these
engagement components. For example, a high BPI generally leads to higher interactions and better social media activity,
thereby contributing to:
Interactions = g(BPI)
Social Media Activity = h(BPI)
Merchandise Sales = i(BPI)
where g, h, and i are functions representing the relationship between BPI and these engagement metrics.
Thus, we can see that: BPI FE
implies that the BPI is a subset of the broader fan engagement metrics, as higher BPI scores generally lead to higher fan
engagement levels across various components.

7
C. BPI Calculation Examples
1) Deep Player Performance Index (DPI) Calculation
MS Dhoni, celebrated for his leadership and finishing abilities, and Chris Gayle, known for his explosive batting style,
represent contrasting styles of play. Comparing them both with existing metric DPPI Calculation:

Chris Gayle’s reputation as one of the best T20 batsmen is built on his remarkable ability to dominate the game with
explosive innings and a high strike rate. His prowess in rapidly accumulating runs and delivering match-winning
performances distinguishes him as a standout player in the format. However, the Deep Player Performance Index (DPPI),
which combines batting average and strike rate into a single measure, does not capture the full breadth of his impact. The
DPPI fails to account for critical elements such as the quality of opposition, the context of his innings, and his ability to
perform under pressure. As such, while the DPPI offers a useful overview, it does not fully reflect the nuances of Gayle’s
extraordinary contributions to T20 cricket.
2) Batsman Performance Index (BPI) Calculation: The Batsman Performance Index (BPI) overcomes the limitations of
simpler metrics by incorporating multiple key performance indicators (KPIs) and traditional metrics. By evaluating a range of
factors, BPI provides a more comprehensive and nuanced analysis of a batsman’s impact. This approach ensures a more
accurate reflection of a player’s true value in T20 cricket, capturing the complexities that single-metric indices might miss.

3) 3. Differences in Evaluation: While both MS Dhoni and Chris Gayle exhibit strong traditional metrics, the BPI
highlights Dhoni’s efficiency and boundary-hitting under pressure, whereas Gayle’s BPI underscores his boundary-hitting
prowess. This comparison illustrates how the BPI model provides a more nuanced understanding of a player’s impact on the
game.
4) 4. Graphical Comparison: A graphical comparison of DPI and BPI scores for elite players such as AB de Villiers, MS
Dhoni, Chris Gayle, and Rohit Sharma provides a clear visualization of the differences in player evaluation. The BPI offers a
more comprehensive metric, incorporating additional performance indicators that are often overlooked by traditional
metrics.

V. DISCUSSION

8
A. Implications for Cricket Stakeholders
1) Teams and Selectors: Strategic Selection: The BPI provides teams and selectors with a nuanced understanding of a
player’s strengths and weaknesses, enabling more informed decision-making. For instance, in high-pressure situations, a
player with a high BPI in pressure-driven metrics might be favored over one with a traditional high average but lower BPI in
clutch moments. This data-driven approach allows teams to strategically build their line-ups, optimizing for specific match
conditions such as pitch type, opposition quality, and match context.
Player Development: The BPI can also serve as a developmental tool. By breaking down a player’s performance into specific,
measurable components, coaches can identify areas for improvement more accurately. For example, if a player has a low BPI
due to a poor boundary percentage, targeted training can be implemented to address this aspect of their game.
Injury Management and Recovery: The BPI may assist in managing player workloads by identifying patterns of declining
performance, which could signal fatigue or injury risk. This proactive approach allows teams to rest players before injuries
become serious, ensuring a healthier and more sustainable squad over a season
2) Media and Commentary: Enhanced Commentary: The BPI offers broadcasters and commentators a robust tool to
enrich their analysis during live games. By integrating BPI metrics into their discussions, they can provide deeper insights into
why certain players perform well under specific conditions or why a player might be struggling. This can make commentary
more engaging and informative for viewers. Narrative Building: The BPI also aids in crafting narratives that resonate with
fans. For instance, a storyline about a player with a high BPI in ”finishing” games could be used to build excitement during a
chase, adding depth to the viewing experience.
3) Fantasy Sports and Gaming: Sophisticated Player Selection: In the fantasy sports industry, BPI can significantly
enhance user experience by offering more sophisticated tools for player selection. Fantasy platforms can incorporate BPI
metrics to help users pick players who are not just high scorers but also contribute significantly in key moments, thereby
increasing the chances of winning.
Engagement and Retention: The use of BPI in fantasy sports can lead to higher user engagement and retention. As users
delve deeper into BPI metrics to refine their selections, they are likely to spend more time on the platform, which increases
their overall engagement and satisfaction.
4) Sponsors and Marketers: Targeted Marketing: Sponsors can leverage BPI to identify players who are not only
performing well but also attracting significant fan attention. By aligning their brands with high-BPI players, sponsors can
maximize their reach and impact, ensuring that their marketing campaigns resonate with the target audience.
Brand Association: High-BPI players who are consistently in the spotlight offer sponsors a reliable and consistent platform for
brand association. These players often have a strong fan following, making them ideal candidates for endorsements and
promotional campaigns.
5) Fan Engagement and Experience: Personalized Content: For fans, the BPI can offer a more personalized and
immersive experience. Digital platforms can use BPI to create custom content, such as video highlights of high-BPI players or
interactive data visualizations that allow fans to explore player performances in detail.
Enhanced Viewing Experience: BPI metrics can be integrated into broadcast graphics, giving fans real-time insights into
player performances. This can make the viewing experience more engaging, as fans can better understand the nuances of
the game and appreciate the strategic elements at play.
Social Media and Digital Interaction: Fans are increasingly active on social media platforms, where they discuss and analyze
player performances. The introduction of BPI could enhance these discussions, providing fans with a more sophisticated
framework to analyze and debate the merits of their favorite players.
6) Fan Behavior Analytics: Understanding the correlation between BPI and fan engagement helps teams,
broadcasters, and sponsors effectively predict and influence fan behavior. By focusing on players with high BPIs, teams can
tailor marketing strategies, broadcasters can create engaging content, and sponsors can align their brands with popular
players. This insight also aids in optimizing ticket pricing and boosting merchandise sales, ensuring that fan engagement is
maximized and strategies are more effective.

VI. CONCLUSION AND FUTURE SCOPE

A. Conclusion

This research paper introduces a sophisticated approach to evaluating batsman performance through the Batsman
Performance Index (BPI). By incorporating multiple metrics such as strike rate, average, boundary percentage, and others,
the BPI offers a comprehensive assessment of a player’s impact on the game. The BPI’s ability to provide nuanced
comparisons between different players—whether contemporaries like AB de Villiers, MS Dhoni, Chris Gayle, and Rohit
Sharma, or players from different eras—demonstrates its superiority over traditional metrics like the Deep Player
Performance Index (DPI), which focuses on limited factors. The development of the Normalized BPI has enabled a fair
comparison of players from different eras by adjusting their statistics to reflect the changing nature of the game. This is

9
particularly evident in the comparison between players like Virat Kohli, Sachin Tendulkar, and Vivian Richards, where the
Normalized BPI provides insights into their overall impact despite differences in playing conditions and opposition quality.
The paper also explores the relationship between high BPI scores and fan engagement, highlighting how players with higher
BPIs tend to attract more attention and interaction from fans. This correlation can be leveraged by teams, broadcasters, and
sponsors to better understand and influence fan behavior, leading to more effective marketing strategies and content
creation. Ultimately, the BPI and Normalized BPI not only enhance our ability to assess player performance with greater
accuracy but also contribute valuable insights into fan engagement, making them essential tools in modern cricket analysis.
This comprehensive approach underscores the importance of considering all relevant metrics in evaluating players and has
the potential to transform how we compare, understand, and appreciate the contributions of cricketing greats across
different eras.

B. Future Scope
The Batsman Performance Index (BPI) utilizes advanced parameters to compare batsmen across different eras, providing a
comprehensive evaluation of their impact on the game. By incorporating a range of performance metrics, the BPI offers a
holistic assessment that accurately reflects a batsman’s influence over time. Future developments include:
• Impact Player Identification: An ”Impact Player” should be evaluated on batting, bowling, and fielding, not just
batting alone. Such players excel across multiple skills, consistently perform in various roles, and adapt well under pressure.
This comprehensive approach ensures that players who can influence the game in multiple ways are accurately recognized
for their overall contribution.
• Injury Risk Prediction: Enhancing the model to predict injury risks, particularly for players with high physical
demands such as fast bowlers or agile fielders. This involves analyzing real-time data on player movements, workloads, and
biomechanics:–
Biomechanics: Use wearable sensors and video analysis to gather data on players’ biomechanics, including joint angles,
muscle strain, and movement efficiency
Pattern Recognition: Develop AI algorithms to recognize patterns associated with past injuries, correlating them with current
biomechanical data and workload metrics.
Risk Scoring: The AI assigns a risk score to each player based on their data, with higher scores indicating a greater likelihood
of injury.
By predicting injury risks, teams can proactively manage player health, reduce injury incidence, and extend players’ careers.
• Applications in Sports Management and Talent Agencies: Fanbase predictions can guide contract negotiations, secure
endorsements, and shape talent development strategies.
• Broadcasting and Media Networks: Media companies can optimize programming and attract higher-paying
advertisers by focusing on players with growing fanbases.
• Merchandising and Retail: Retailers can improve product development and sales forecasting by aligning
merchandise production with predicted fanbase trends.
• Fantasy Sports: The BPI enhances fantasy league experiences by providing accurate player performance
assessments. By incorporating advanced metrics, the BPI dynamically adjusts player valuations based on form and trends,
helping fans make informed decisions and boosting their success in fantasy leagues.
• Event Management and Ticketing: Event organizers can plan promotions and set pricing strategies around players
expected to attract more fans, optimizing attendance and revenue.
• Sportswear and Equipment Brands: Brands can enhance product endorsements and launch successful
collaborations by selecting players with growing fanbases.
• Gaming and Esports: Game developers and esports platforms can capitalize on popular players by integrating them
into games or highlighting them in content, boosting engagement. • Publishing and Content Creation: Publishers and content
creators can focus on producing and promoting content related to players with increasing fanbases, driving higher audience
interest.
Publishing and Content Creation: Publishers and content creators can focus on producing and promoting content related to
players with increasing fanbases, driving higher audience interest

VII. REFERENCES

REFERENCES
[1] [1] A new Machine Learning based Deep Performance Index for Ranking IPL T20 Cricketers. Available online:
https://www.researchgate. net/publication/298801732 A new Machine Learning based Deep Performance Index for
Ranking IPL T20 Cricketers

10
[2] [2] TheCricketCouch, “A simple metric to understand batting efficiency in [Online]. the Available: IPL,”
Thecricketcouch.com, 15-Jun-2012. http://thecricketcouch.com/blog/2012/06/ 15/a-simple-metric-to-
understandbatting-efficiency-in-the-ipl/. [Accessed: 24-Aug-2024].
[3] [3] Publishing India. Available publishingindia.com/GetBrochure.aspx?query= online: http://
UERGQnJvY2h1cmVzfC81NjI2LnBkZnwvNTYyNi5wZGY=
[4] [4] Chris Gayle’s statistics. Available online: https://www.espncricinfo.com/
cricketers/chris-gayle-51880/bowlingbatting-stats
[5] [5] MS Dhoni’s statistics. Available online: https://www.espncricinfo.com/ cricketers/ms-dhoni-28081/bowling-batting-
stats
[6] [6] Team Selection Strategy in IPL 9 using Random Forests Algorithm. Available online:
https://www.researchgate.net/publication/301335652 Team Selection Strategy in IPL 9 using Random Forests Algorithm?
tp=eyJjb250ZXh0Ijp7ImZpcnN0UGFnZS
[7] [7] Indian Premier League. Available online: https://en.wikipedia.org/wiki/ Indian Premier League
[8] [8] Clarke, S. R., “Dynamic programming in one day cricket optimal scoring rates,” Journal of the Operational Research
Society, 50, 1988, pp 536– 545.
[9] [9] Kimber, A. C. and Hansford, A. R., “A Statistical Analysis of Batting in Cricket,” Journal of Royal Statistical Society,
156, 1993, pp 443 455.
[10] [10] Damodaran, U., “Stochastic Dominance and Analysis of ODI Batting Performance: The Indian Cricket Team,
19892005,” Journal of Sports Science and Medicine, 5, 2006, pp 503– 508.
[11] [11] Barr, G. D. I., and Kantor, B. S., “A Criterion for Comparing and Selecting Batsmen in Limited Overs Cricket,”
Journal of the Operational Research Society, 55, 2004, pp 1266-1274.
[12] [12] Borooah, V. K., and Mangan, J. E., “The ‘Bradman Class’: An Explo ration of Some Issues in the Evaluation of
Batsmen for Test Matches, 1877–2006.” Journal of Quantitative Analysis in Sports, 6 (3), Article 14, 2010.
[13] [13] Norman, J. and Clarke, S. R., “Dynamic programming in cricket: Batting on sticky wicket,” Proceedings of the 7th
Australasian Conference on Mathematics and Computers in Sport, 2004, pp 226– 232.
[14] [14] Ovens, M. and Bukkit, B., “A mathematical modelling approach to one day cricket batting orders,” Journal of Sports
Science and Medicine, 5, 2006, pp 495-502. [
[15] 15] Lewis, A., “Extending the Range of Player-Performance Measures in One-Day Cricket,” Journal of Operational
Research Society, 59, 2008, pp 729-742.
[16] [16] Van Staden, P., “Comparison of Cricketers’ Bowling and Batting Perfor mance using Graphical Displays,” Current
Science, 96, 2009, pp 764 766.
[17] [17] Lakkaraju, P., and Sethi, S., “Correlating the Analysis of Opinionated Texts Using SAS® Text Analytics with
Application of Sabermetrics to Cricket Statistics,” Proceedings of SAS Global Forum 2012, 136-2012, pp 1-10.
[18] [18] Lemmer, H., “A Measure for the Batting performance of Cricket Play ers,” South African Journal for Research in
Sport, Physical Education and Recreation, 26, 2004, pp 55-64.
[19] [19] Lemmer, H., “An Analysis of Players’ Performances in the First Cricket Twenty20 World Cup Series,” South
African Journal for Research in Sport, Physical Education and Recreation, 30, 2008, pp 71-77.
[20] [20] Lemmer, H., “The Single Match Approach to Strike Rate Adjustments in Batting Performance Measures in Cricket,”
Journal of Sports Science and Medicine, 10, 2012, pp 630-634.
[21] [21] Saikia, Hemanta and Bhattacharjee, Dibojyoti, “A Bayesian Classifi cation Model for Predicting the Performance of
All-Rounders in the Indian Premier League.” Available online: http://papers.ssrn.com/sol3/ papers.cfm?abstract
id=16220
[22] [22] Fantasy sports statistics. Available online: http://www.espncricinfo.com/ india/content/player/28081.htm
[23] l [23] IPL statistics of each player. Available online: http://www.iplt20.com/
teams/royal-challengersbangalore/squad/236/chris-gayl. Plant Methods 15, 92 (2019).
https://doi.org/10.1186/s13007-019-0475-z
[24] [24] Rediff, Lead,” “ICC World Cup: De Villiers Maintains Big Available online: http://www.rediff.com/cricket/report/
icc-world-cup-devilliers-maintains-big-lead-shami-rises-to-7th-in-most-valuable-player-table/ 20150320.html
[25] [25] Kumar, Amit and Sindhu, Ritu, “Reflection against perception: Data Analysis of IPL Batsmen,” International
Journal of Engineering Science Invention, Vol. 3, Issue 6, June 2014, pp 7– 11. ISSN No. 2319-6734.
[26] [26] Deb, Kalyanmoy and Jindal, Abhilash, “Multiobjective Optimization and decision making approaches to cricket
team selection,” Applied Soft Computing, Vol. 13, 2013, pp 402– 414

11