Please use this identifier to cite or link to this item:
https://gnanaganga.inflibnet.ac.in:8443/jspui/handle/123456789/15421
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Stebinsabu | - |
dc.contributor.author | Naik, Ramvilas V | - |
dc.contributor.author | Sibhe, S | - |
dc.contributor.author | Srivastava, Anoop Kumar | - |
dc.date.accessioned | 2024-04-20T10:53:14Z | - |
dc.date.available | 2024-04-20T10:53:14Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://gnanaganga.inflibnet.ac.in:8080/jspui/handle/123456789/15421 | - |
dc.description.abstract | The Automated Data Analysis and Machine Learning System is a ground-breaking initiative designed to help users with dataset processing, visualization, and identification of appropriate machine learning models for accurate predictions. In the data-driven world of today, it is essential to have effective tools at your disposal that automate data analysis, provide insightful information, and aid in decision-making. By offering a complete management solution for jobs including data analysis and machine learning, this system seeks to satisfy those criteria. Beginning with data input and preparation, the system incorporates several crucial functionalities. User-provided datasets are cleaned, processed, and made ready for analysis after being input. In order for the data to be processed later, it must be in the proper format. Additionally, the system performs exploratory data analysis (EDA) to give consumers a more comprehensive knowledge of their data. Users obtain understanding of the distribution, connections, and trends within the dataset through a variety of visualizations such histograms, scatter plots, and correlation matrices. In addition, summary statistics are computed, outliers are discovered, and missing values are found. Users are now able to make knowledgeable choices about the data quality and potential preprocessing processes thanks to these findings. The system uses feature engineering approaches to improve the dataset by extracting valuable features or producing new ones. Subsequent machine learning models perform better thanks to transformation, feature selection, and dimensionality reduction techniques. These methods aid in noise reduction, model interpretability improvement, and general prediction accuracy improvement. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Alliance College of Engineering and Design, Alliance University | en_US |
dc.subject | Automated Data Analysis | en_US |
dc.subject | Machine Learning System | en_US |
dc.subject | Exploratory Data Analysis (Eda) | en_US |
dc.subject | Dimensionality Reduction Techniques | en_US |
dc.title | Automated Data Analysis and Ml Platform | en_US |
dc.type | Other | en_US |
Appears in Collections: | Dissertations - Alliance College of Engineering & Design |
Files in This Item:
File | Size | Format | |
---|---|---|---|
CSE_G28_2023.pdf Restricted Access | 2.39 MB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.