Cricket Matches Prediction using Data Science

Objective

To predict the outcome of the cricket match result using data science based on the historical and current data.

Project Overview

In recent times, data science predictive modeling plays a crucial role in the sports. Cricket is one of the famous sports in India. On the given day, any team can win the match with its performance. This makes the challenge in predicting the accurate outcome of the cricket match.
The cricket game involves 3 formats – namely, Test Matches, ODIs andT20s. This project concentrates on the latest format of the game T20. To predict the result of the T20 game, we analyze the type of ground, teams past performance, batting and bowling potentials of the 11 players of both teams using their past performance. Another important parameter considered for prediction is toss decision factor.

Proposed System

With the advanced technology in today’s world, we are in need of predicting the outcome of the match. This paper focuses on predicting the outcome of the T20 matches. Supervised learning algorithms are used to predict the outcome of the match. The proposed system architecture is shown in the figure.

 

Cricket Matches Prediction Modules

Module 1:Data Selection

The required data is collected from the cricket website. The data should consist of player details with all features.

Batting records

• Runs scored
• Strike rate
• Batting average
• Highest score
• Home/ Away
• Opposite team

Bowling records

• Balls bowled
• Wickets taken
• Economy rate
• Best bowling
• Number of 4 wickets haul
• Home/ Away
• Opposite team

Module 2: Data Preparation
Data preparation is an important step in any data science project. It consists of data cleaning, integration, normalization, transformation, reduction, feature extraction, and selection, etc.

Module 3: Correlation
In a T20 match, toss is the crucial factor in deciding the outcome of the match. Most of the toss-winning the captain choose to field first. It’s because of the perception is that, the team fielding first winning the most matches in the T20 match. To identify this relation, correlation techniques are used. Here, the correlation between toss winner and match winners is analyzed.

Module 3 : Implementation of Supervised Learning
The required supervised learning algorithm is applied to the given data set. This algorithm is applied to the data set to analyze the player performance and the accuracy is calculated. The interesting relationships between the player performances are identified using association rules. Predictive analytical techniques are used to predict the outcome of the T20 match using previous historical data and current data.

Module 4 : Predicting the Outcome of the Match
Prediction is a data mining function that discovers the future behaviors. Using the predictive analytics method, the outcome of the cricket match is predicted. Here, supervised learning approach is used.

Software Requirements

• Weka 3.8
• Netbeans
• SQL Server

Hardware Requirements

• Hard Disk – 1 TB or Above
• RAM required – 4 GB or Above
• Processor – Core i3 or Above

Sentiment Analysis on E-Commerce Sites

 

Objective

To analyse the sentiments of people on various e-commerce sites to understand the people’s view or Sentiment Analysis on E-Commerce Sites. This will help the e-commerce sites to enhance their method.

Project Overview

This project concentrates on Twitter sentiment analysis since it is a better approximation of public sentiment as opposed to conventional internet articles and web blogs. The reason is that the amount of relevant data is much larger for the twitter, as compared to traditional blogging sites.

Sentiment analysis of public is important in any business. This could be done by analyzing overall public sentiment towards that product with respect to time and using tools for finding the public sentiment. This can also estimate how well the product is responding to the market by classifying tweets into the positive, negative and neutral. Using this information, the product efficiency can be enhanced.

Proposed System

The sentiment analysis of the user on an e-commerce site is proposed to provide the better understanding and people’s view of the particular product by displaying the classified user sentiment at the high accuracy rate. This would help to purchase the better product by people and also help the product developers to enhance their product.The proposed system architecture is shown in the figure.

List of Modules for Sentiment Analysis on E-Commerce Sites 

• Data Gathering
• Attributes Collection
• Statistics
• Result and Analysis
• Data Visualization

Module 1: Data Collection

The dataset for this project is collected from the twitter using R tool for e-Commerce site. Data is collected for top three e-commerce sites such as Flipkart, Amazon, and Snapdeal. TwitterAPI is used to extract the data from Twitter.

Module 2: List of Attributes

The collected dataset consists of following attributes.

• Row no
• Id
• Polarity_connection
• Subjectivity_connection
• Polarity
• Subjectivity
• Created-At
• From-User
• From-User-Id
• To-User
• To-User-Id
• Language
• Text

 Module 3: Statistics

Sentiment analysis of e-commerce sites will be used as a recommendation to the new users or the existing users. Also, sentiment analysis will help a company to boom their business and provide better quality to their customers. Here the twitter texts are classified into Positive, Negative and Neutral. Positive opinion words are used to express desired feelings while negative opinion words are used to express undesired feelings.

Module 4: Result and Analysis

Thus the data collection on various products statistical view on tweets such as classification of positive, negative and neutral tweets has been performed. The classification algorithm will be used to obtain the final outcome.

Module 5: Data Visualization

The classified data is analyzed, and the result is represented in the form of a bar chart, pie chart, and graph and word cloud. The graphical plot of the sentiment using Tableau tool makes it easy to evaluate performance e-commerce sites. The graphical plot of the sentiment using business intelligence tool makes it easy to evaluate the performance of classification algorithms.

 Software Requirements

• R Programming
• TwitterAPI
• Tableau

Hardware Requirements

• Hard Disk – 1 TB or Above
• RAM required – 8 GB or Above
• Processor – Core i3 or Above

Student Performance Analysis Prediction Using Data Analytics

 

Objective

To analyse the students performance based on their academic data using data mining techniques.

Project Overview

In this technological world, data storage and analysis are a big challenge. The ultimate goal of this project is aimed at better analysis with improved accuracy of data. Its requirement is so simple, that needs only the data sources, which is then processed to compute the results in the form of the report through which we can easily analyze the performance of the student in an efficient way.

It also focuses on analyzing data which helps in categorizing and thereby motivating the students in their academics as well as flavoring the staffs to improvise the students to the next level.Finally, the students are grouped as a good performer, average performer, a bad performer based on their result analyzed from their academic data.

Proposed System

Career building is the most cherished part of every college student. For a graduate, it is necessary to have immense knowledge in their domain to get placed in a reputed company. This system applies data mining techniques to the academic dataset. The Academic data includes the Internal marks and the Assignment marks. The final semester marks are predicted from the internal marks each student.

The proposed system architecture is shown in the figure.

Figure: Proposed System Architecture

Module 1:Data Selection

The required data is collected from the academic institutions. The data should consist of student details with internal marks and assignment marks.

Module 2: Data Preparation

Data preparation is an important step in the data mining process. Data pre-processing, includes cleaning, normalization, transformation, feature extraction, and selection, etc.

Module 3: Implementation of Data Mining Techniques

The required data mining algorithm is implemented using Java in Netbeans. These algorithms are applied to the data set to analyze the student academic performance and the accuracy are calculated.

Module 4: Predicting End Semester Grades

Prediction is a data mining function that discovers the future characteristics of the data. The relationships between co-occurring items are expressed as association rules. Predictive techniques rules are used to predict the final grades of the students using cumulative test mark and assignment marks.

Module 5: Grouping Students Using Simple Cluster

The students are grouped based on their end semester grades. The good performing students are grouped in one group, the average performing students are grouped as a group and finally, poor performing students are grouped in a group.

Module 6: Data Visualization

The association between theextracted results is found, to give the accurate analysis of results. These analyzed results are then displayed in the pictorial format of bar charts for the easy analysis and better understanding of the user.

Software Requirements

• Weka 3.8
• Netbeans
• Visual Studio
• SQL Server 2008

Hardware Requirements

• Hard Disk – 1 TB or Above
• RAM required – 4 GB or Above
• Processor – Core i3 or Above

Tableau in Institutions for Better Insight

 

Objective

To implement the business intelligence in institutions using Tableau for the better insight using Tableau Projects. This will help the institutions to enhance their process.

Project Overview

The mark and attendance of the student are used for the analysis, extracting the relationship among attributes in several constraints and possibilities. Attendance and mark analysis system are built with facilitating easy analysis by highlighting the hidden association in the data set. The more stable working environment needs to be developed.

Existing System

Most of the institutions use some type of software to maintain their data in digital format. The main focus of the software is to store, update and retrieve the required data easily. The existing system mainly concentrates on the data storage in the single repository rather the analysis of the data, is much difficult to process. This existing mark and attendance reporting system satisfy only the basic needs of the end users. Weekly, monthly and daily reports can be extracted from the existing system but extracting complex community reports is impossible in the existing system. This project adds over that and focuses more on the data analytics.

Problem Definition

This system satisfies only the basic requirements such as the monthly, weekly and daily report of attendance record of the students along with the course description.

Proposed System

Proposed System of this project can be stated in terms of different categories as visualizing, comparing and analyzing. In this system, requirements such as analysis and relationship of the complex reports are achieved using the following,

• Basic Statistics and Business Intelligence
• Data Analytics

This also includes the extraction of association between various attributes and the hidden relationship between them. Finally, data analytics is used to filter those required data from the entire dataset.

Module 1 : Requirement Analysis and Data Pre-Processing:

In this module, the requirements are collected from faculties and students. Some of the requirements include:

• Finding the students who secured top and bottom 5 marks.
• Comparative analysis among students.
• Finding the Impact on marks due to attendance.
• For analysis, student internal marks along with their attendance and assignment marks will be collected from the institutions.

Module 2: Statistics

In this module, the marks and attendance of students are analyzed. From this above statistics, we get the average details of the given dataset, like maximum minimum internal grade and highest lowest percentage. With the above statistics, we are going to analyze the marks of the students in different constraints using various tools.

Module 3: Business Intelligence

The concept of business intelligence is included in the project by using Tableau tool. The tool helps in finding the relational flow graph for the student course wise, exam wise top5 and bottom 5. It is also helpful in finding attendance and mark based on different categories.

Module 4-Data Mining

The concept of data mining is included in the project by using the Rapid Miner and R tool. The algorithm of data mining is imported from the rapid miner and working part of the algorithm is implemented as built-in and the required graph is displayed.

Apriori Algorithm

The Apriorialgorithm is implemented in Rapid Miner as it includes the property of the association.

• Rules (Top 5 – Support)
  • Top 5 support is used to segregate the top 5 records from the entire dataset, which helps in easy retrieval and analysis of the statistical data.
• Rules (Bottom 5 – Support)
  • Bottom 5 support is used to segregate the bottom 5 records from the entire dataset, which helps in easy retrieval and analysis of the statistical data.

Software Requirements

• MySQL Server
• Tableau
• R
• RapidMiner

Hardware Requirements

• Hard Disk – 1 TB or Above
• RAM required – 8 GB or Above
• Processor – Core i3 or Above

Trending YouTube Video Statistics

 

Objective

To extract the useful information from the trending YouTube video using the statistics modelling techniques.

Project Overview

YouTube is the well-known video sharing platform in the world. The website maintains the mostly viewed topmost videos and trending videos. Most of the trending videos are music videos, comedy, celebrity performances, sports incidents and latest viral videos. To identify the trending videos, it uses the factors like,

• Number of Views
• Shares
• Comments
• Likes

System Design

Proposed YouTube Video Statistics System of this project concentrates on the categories such as visualizing, comparing and analyzing. In this system, the required outcome is obtained using the following,

• Basic Statistics
• Business Intelligence
• Data Analytics
• Machine Learning
• Predictive Analytics

List of modules are

• Data set collection
• Data preparation
• Data analytics
• Data visualization

Module 1 : Data Set Collection

The required data set was collected from YouTube using the YouTube API.The collected data set consists of daily trending videos of last few years. The gathered data includes the regions such as USA, Canada, France and Great Britain. The data includes the factor like channel title, video title, time published, number of tags, number of views, number of likes, number of dislikes, description of the video and comment count.

List of Attributes

The YouTube Video Statistics data set consist of two parts. One is a comment and another one is video statistics. Here video_id is used as a unique field.

The attributes of the video file,

• video_id
• video_title
• date
• channel_title
• category_id
• views
• likes
• dislikes
• thumbnail_link
• tags

The attributes of the comments file

• video_id
• comment_text
• likes
• replies

Module 2: Data Preparation

Data preparation is one of the important step and time-consuming process in the data mining process. Data pre-processing, includes cleaning, transformation, and attribute selection, etc.

Module 3: Data Analytics

From the collected data set following things can be done for the better understanding and better decision making in the future.

• Categorising the videos
  • Comments play a huge factor here.
• Different forms of sentiment analysis
  • Supervised learning algorithms used here.
• Auto-generation of comments
  • Machine learning algorithms play a huge role here.
• Predicting the popularity of the video in advance
  • Predictive analytics used here.

Module 4 : Data Visualization

The hidden information between the extracted results is found. These patterns are then displayed in the pictorial format of bar charts for the easy analysis and better understanding. The resultant chart contains relative comparisons between two features combination of the data set. The analyzed result is obtained a relationship between all items as visualized form.

More attributes can be added to the data set while collecting data. This will help to gain much better understanding. Deeper analyzes of the project give furthermore efficient and effective analyzes in the project.

Software Requirements

• Tableau
• R

Hardware Requirements

• Hard Disk – 1 TB or Above
• RAM required – 8 GB or Above
• Processor – Core i3 or Above

Download Abstract