Predicting Results of Indian Premier League T-20 Matches using Machine Learning

Agrawal, Shilpi; Singh, Supriya; Sharma, Jayash Kumar

doi:10.1109/csnt.2018.8820235

Cited by 26 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We performed inference using pathfinder, a recently developed approach to inferring posteriors using pseudo-Hessian optimizers applied to a variational inference objective 30 . We chose a variational inference approach rather than MCMC as MCMC approaches have been shown to be computationally very intensive when sampling over large discrete graph structures 23,24,31,32 . We termed this statistical method LLCB.…”

Section: Resultsmentioning

confidence: 99%

“…Direct effects are useful because they facilitate a coherent interpretation of gene networks as directed probabilistic graphical models. Our approach differs from many other gene networks in two key ways: 1) because our network is derived from experimental perturbations, the edges are much more likely to be causal than the edges in a network estimated from observational co-expression data, where the constituent variation is often of an unknown genesis; 2) our method enables estimation of possibly cyclic graphs, rather than the common restriction to directed acyclic graphs (DAGs) 20,22–24 . Human genetics has identified several examples of cyclic regulatory behavior 25 , so the restriction of GRNs to DAGs represents an artificial constraint that we circumvent with appropriate statistical technology.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gene regulatory network inference from CRISPR perturbations in primary CD4+ T cells elucidates the genomic basis of immune disease

Weinstock,

Arce,

Freimer

et al. 2023

Preprint

View full text Add to dashboard Cite

The effects of genetic variation on complex traits act mainly through changes in gene regulation. Although many genetic variants have been linked to target genes in cis, the trans-regulatory cascade mediating their effects remains largely uncharacterized. Mapping trans-regulators based on natural genetic variation, including eQTL mapping, has been challenging due to small effects. Experimental perturbation approaches offer a complementary and powerful approach to mapping trans-regulators. We used CRISPR knockouts of 84 genes in primary CD4+ T cells to perturb an immune cell gene network, targeting both inborn error of immunity (IEI) disease transcription factors (TFs) and background TFs matched in constraint and expression level, but without a known immune disease association. We developed a novel Bayesian structure learning method called Linear Latent Causal Bayes (LLCB) to estimate the gene regulatory network from perturbation data and observed 211 directed edges among the genes which could not be detected in existing CD4+ trans-eQTL data. We used LLCB to characterize the differences between the IEI and background TFs, finding that the gene groups were highly interconnected, but that IEI TFs were much more likely to regulate immune cell specific pathways and immune GWAS genes. We further characterized nine coherent gene programs based on downstream effects of the TFs and linked these modules to regulation of GWAS genes, finding that canonical JAK-STAT family members are regulated by KMT2A, a global epigenetic regulator. These analyses reveal the trans-regulatory cascade from upstream epigenetic regulator to intermediate TFs to downstream effector cytokines and elucidate the logic linking immune GWAS genes to key signaling pathways.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Gene regulatory network inference from CRISPR perturbations in primary CD4+ T cells elucidates the genomic basis of immune disease

Weinstock,

Arce,

Freimer

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Priyanka et al [4] predicted the outcome of IPL-2020 by employing Data Mining Algorithms on IPL datasets from 2008-2019, achieving an accuracy of 82.73%. Kansal et al [5] utilized Data Mining Techniques to predict player evaluation in IPL based on datasets from 2008-2019. They employed data mining algorithms to assess player performance, determine their base price, and aid in player selection for the IPL.…”

Section: IImentioning

confidence: 99%

Analyzing Key Factors for Second Innings Triumph in IPL Using Machine Learning

et al. 2023

IJRASET

View full text Add to dashboard Cite

bstract: The Indian Premier League (IPL) has emerged as one of the most captivating and celebrated cricket tournaments worldwide. With its unique blend of sporting excellence, entertainment, and fierce competition, the IPL has captured the imagination of millions of cricket enthusiasts. In this era of data-driven decision-making, harnessing the power of statistical analysis and predictive modelling can provide valuable insights into the dynamics and outcomes of IPL matches. This research paper aims to explore on the analysis of factors contributing to a team's success in the second innings of IPL matches using exploratory data analysis (EDA) and logistic regression modelling. The EDA section will uncover patterns and correlations among variables such as team composition, batting order, run rate, power-play performance, bowling strategies, fielding efficiency, and match conditions. Logistic regression modelling will be applied to develop a predictive model that forecasts the likelihood of a team's victory in the second innings based on the identified factors. The model will be trained, validated, and evaluated using historical data.

show abstract

“…In the past, a number of researchers have made contributions to outcome prediction. Agrawal et al, [1] explored the issue of anticipating the match's unknown winner in the IPL. They applied machine learning models like Support Vector Machine, Classification Tree, and Naive Bayes Algorithm.…”

Section: Related Workmentioning

confidence: 99%

Win probability prediction for IPL match using various machine learning techniques

Sanaboina,

Kumar

2023

Int. J. Eng. Comput. Sci.

View full text Add to dashboard Cite

The paper's primary objective is to predict the win probability for both the batting and bowling teams in the IPL (Indian Premier League) match using various machine learning algorithms. This paper tackles the challenge of forecasting the result of a match determined by the Target, Net Run Rate (NRR), Current Run Rate (CRR), Score, Fall of Wickets, and the Technique each team employs during each game. For making predictions, three machine learning models Logistic Regression, Random Forest, and Naive Bayes were utilized. The Logistic Regression and Random Forest Algorithms provide the best results and have an accuracy rate of 82% and 96% respectively whereas Naïve Bayes has an accuracy rate of 63%.

show abstract

Predicting Results of Indian Premier League T-20 Matches using Machine Learning

Cited by 26 publications

References 6 publications

Gene regulatory network inference from CRISPR perturbations in primary CD4+ T cells elucidates the genomic basis of immune disease

Gene regulatory network inference from CRISPR perturbations in primary CD4+ T cells elucidates the genomic basis of immune disease

Analyzing Key Factors for Second Innings Triumph in IPL Using Machine Learning

Win probability prediction for IPL match using various machine learning techniques

Contact Info

Product

Resources

About