scholarly journals Analysis and Outcome Prediction of Crowdfunding Campaigns

2022 ◽  
Vol 12 (1) ◽  
pp. 1-14
Author(s):  
Parmeet Kaur ◽  
Sanya Deshmukh ◽  
Pranjal Apoorva ◽  
Simar Batra

Humongous volumes of data are being generated every minute by individual users as well as organizations. This data can be turned into a valuable asset only if it is analyzed, interpreted and used for improving processes or for benefiting users. One such source that is contributing huge data every year is a large number of web-based crowd-funding projects. These projects and related campaigns help ventures to raise money by acquiring small amounts of funding from different small organizations and people. The funds raised for crowdfunded projects and hence, their success depends on multiple elements of the project. The current work predicts the success of a new venture by analysis and visualization of the existing data and determining the parameters on which success of a project depends. The prediction of a project’s outcome is performed by application of machine learning algorithms on crowd-funding data stored in the NoSQL database, MongoDB. The results of this work can prove beneficial for the investors to have an estimate about the success of a project before investing in it.

An effective representation by machine learning algorithms is to obtain the results especially in Big Data, there are numerous applications can produce outcome, whereas a Random Forest Algorithm (RF) Gradient Boosting Machine (GBM), Decision tree (DT) in Python will able to give the higher accuracy in regard with classifying various parameters of Airliner Passengers satisfactory levels. The complex information of airline passengers has provided huge data for interpretation through different parameters of satisfaction that contains large information in quantity wise. An algorithm has to support in classifying these data’s with accuracies. As a result some of the methods may provide less precision and there is an opportunity of information cancellation and furthermore information missing utilizing conventional techniques. Subsequently RF and GBM used to conquer the unpredictability and exactness about the information provided. The aim of this study is to identify an Algorithm which is suitable for classifying the satisfactory level of airline passengers with data analytics using python by knowing the output. The optimization and Implementation of independent variables by training and testing for accuracy in python platform determined the variation between the each parameters and also recognized RF and GBM as a better algorithm in comparison with other classifying algorithms.


2017 ◽  
Vol 28 ◽  
pp. v518
Author(s):  
H-L. Wong ◽  
T. Luechtefeld ◽  
A. Prawira ◽  
Z. Patterson ◽  
J. Workman ◽  
...  

2020 ◽  
Vol 11 ◽  
Author(s):  
Shakiru A. Alaka ◽  
Bijoy K. Menon ◽  
Anita Brobbey ◽  
Tyler Williamson ◽  
Mayank Goyal ◽  
...  

Detection of spam review is an important operation for present e-commwebsites and apps.We address the issue on fake review detection in user reviews in e-commerce application, which wasimportant for implementing anti-opinion spam.First we analyze the characteristics of fake reviews and we apply the machine learning algorithms on that data. Spam or fake reviews of the itemsreducing the reliability of decision making and competitive analysis.The presence of fake reviews makes the customer cannot make the right decisions of sellers, which can also causes the goodwill of the platform decreased. There is a chance of leaving appraisals via web-based networking media systems whether states or harming by spammers on specific item, firm alongside their answers by recognizing these spammers just as in like manner spams so as to understand the assessments in the interpersonal organizations sites, we exist a stand-out structure called Netspam which uses spam highlights for demonstrating tribute datasets as heterogeneous subtleties systems to guide spam location treatment directly into gathering issue in such systems.


2018 ◽  
Vol 45 (5) ◽  
pp. E7 ◽  
Author(s):  
Nikhil Paliwal ◽  
Prakhar Jaiswal ◽  
Vincent M. Tutino ◽  
Hussain Shallwani ◽  
Jason M. Davies ◽  
...  

OBJECTIVEFlow diverters (FDs) are designed to occlude intracranial aneurysms (IAs) while preserving flow to essential arteries. Incomplete occlusion exposes patients to risks of thromboembolic complications and rupture. A priori assessment of FD treatment outcome could enable treatment optimization leading to better outcomes. To that end, the authors applied image-based computational analysis to clinically FD-treated aneurysms to extract information regarding morphology, pre- and post-treatment hemodynamics, and FD-device characteristics and then used these parameters to train machine learning algorithms to predict 6-month clinical outcomes after FD treatment.METHODSData were retrospectively collected for 84 FD-treated sidewall aneurysms in 80 patients. Based on 6-month angiographic outcomes, IAs were classified as occluded (n = 63) or residual (incomplete occlusion, n = 21). For each case, the authors modeled FD deployment using a fast virtual stenting algorithm and hemodynamics using image-based computational fluid dynamics. Sixteen morphological, hemodynamic, and FD-based parameters were calculated for each aneurysm. Aneurysms were randomly assigned to a training or testing cohort in approximately a 3:1 ratio. The Student t-test and Mann-Whitney U-test were performed on data from the training cohort to identify significant parameters distinguishing the occluded from residual groups. Predictive models were trained using 4 types of supervised machine learning algorithms: logistic regression (LR), support vector machine (SVM; linear and Gaussian kernels), K-nearest neighbor, and neural network (NN). In the testing cohort, the authors compared outcome prediction by each model trained using all parameters versus only the significant parameters.RESULTSThe training cohort (n = 64) consisted of 48 occluded and 16 residual aneurysms and the testing cohort (n = 20) consisted of 15 occluded and 5 residual aneurysms. Significance tests yielded 2 morphological (ostium ratio and neck ratio) and 3 hemodynamic (pre-treatment inflow rate, post-treatment inflow rate, and post-treatment aneurysm averaged velocity) discriminants between the occluded (good-outcome) and the residual (bad-outcome) group. In both training and testing, all the models trained using all 16 parameters performed better than all the models trained using only the 5 significant parameters. Among the all-parameter models, NN (AUC = 0.967) performed the best during training, followed by LR and linear SVM (AUC = 0.941 and 0.914, respectively). During testing, NN and Gaussian-SVM models had the highest accuracy (90%) in predicting occlusion outcome.CONCLUSIONSNN and Gaussian-SVM models incorporating all 16 morphological, hemodynamic, and FD-related parameters predicted 6-month occlusion outcome of FD treatment with 90% accuracy. More robust models using the computational workflow and machine learning could be trained on larger patient databases toward clinical use in patient-specific treatment planning and optimization.


2018 ◽  
Vol 45 (7) ◽  
pp. 3449-3459 ◽  
Author(s):  
Timo M. Deist ◽  
Frank J. W. M. Dankers ◽  
Gilmer Valdes ◽  
Robin Wijsman ◽  
I‐Chow Hsu ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document