Performance Prediction and Analysis using Decision Tree Algorithms

A Abstract Assay from 2011 to 2014 on Student’s Bookish Achievement Anticipation and Assay appliance Accommodation Timberline Algorithms

Abstract— Success of any educational convention depends aloft the success of the acceptance of institute. Student’s achievement anticipation and its assay are capital for advance in assorted attributes of acceptance like final grades, appearance etc. This anticipation helps agents in identification of anemic acceptance and to advance their scores. Assorted abstracts mining techniques like classification, clustering, are acclimated to accomplish analysis. In this cardboard accomplishing of assorted accommodation timberline algorithms ID3, J48/C4.5, accidental tree, Multilayer Perception, Aphorism Based and accidental backwoods accept been advised for student’s achievement anticipation and analysis. The WEKA apparatus is acclimated to accomplish evaluation. To appraise the achievement allotment breach adjustment or cantankerous validation adjustment is used. Capital cold abaft this assay is to advance student’s performance. This assay cardboard explores the use of assorted accommodation timberline algorithms for student’s bookish achievement anticipation and its analysis.

Keywords— EDM, Accommodation tree, J48, accidental tree, ID3, Multilayer Perception, CART, IBI.

I. Introduction

A. Abstracts Mining and Educational Abstracts Mining(EDM)

Data mining is a action of demography out advantageous advice and patterns from ample aggregate of data. Abstracts Mining is acclimated for analytic problems by allegory abstracts that is present in the databases. [1]

Educational Abstracts Mining (EDM) is a action which is anxious with developing assorted techniques or methods for extracting the altered types of abstracts that appear from educational settings, and use of those methods for bigger compassionate of students. Capital uses of EDM accommodate apprentice achievement anticipation and belief acceptance acquirements to advance improvements in accepted educational practice. [2]

B. Apprentice Achievement Anticipation and Analysis

In apprentice achievement prediction, we adumbrate the alien amount of a capricious that defines the student. In educational sector, the mostly predicted ethics are student’s performance, their marks, ability or score. Student’s achievement anticipation is actual accepted appliance of DM in apprenticeship sector. Altered techniques and models are activated for anticipation and assay of student’s achievement like accommodation trees, neural networks, aphorism based systems, Bayesian networks etc. This assay is accessible for addition in admiration student’s achievement i.e. anticipation about student’s success in a advance and anticipation about student’s final brand on the base of appearance taken from logged data. [2][3]

This cardboard is organized as follows: In area II we present appointment accompanying to apprentice achievement anticipation and analysis. In area III we present allusive abstraction of survey. Conclusion is presented in area IV. In area V we altercate approaching scope.

II. RELATED WORK

Considering the improvements appropriate in acceptance grades or scores, abstract assay has been surveyed based on apprentice achievement anticipation and assay appliance accommodation timberline algorithms.

Brijesh Kumar Baradwaj, Saurabh Pal [5] (2011) accept discussed that acceptance achievement is advised by centralized marks and final results. Abstracts set of 50 acceptance was acclimated in this abstraction which was taken from MCA administration of VBS Purvanchal University, Uttar Pradesh. Advice like antecedent division marks, attendance, and appointment and chic assay marks from antecedent database of students. They accept acclimated accommodation timberline algorithms for apprentice achievement anticipation and analysis. This all-embracing abstraction will advice adroitness associates in convalescent student’s array for approaching examinations.

R. R. Kabra, R. S. Bichkar [11] (Dec. 2011) calm abstracts from S.G.R. academy of engineering and management, Maharashtra. They calm abstracts from 346 acceptance of engineering aboriginal year. Appraisal was performed appliance J48 algorithm by 10 bend cantankerous validation. The accurateness of J48 algorithm was 60.46%. This archetypal is acknowledged in anecdotic the acceptance who are acceptable to fail. So it will be accessible for accretion achievement of students.

Surjeet Kumar Yadav, Saurabh Pal [6] (2012) conducted assay on 90 acceptance of engineering administration (session 2010) from VBS Purvanchal University, Uttar Pradesh. ID3, C4.5 and CART accommodation timberline algorithms were acclimated for evaluation. Appraisal was performed appliance 10 bend cantankerous validation method. It has been begin that C4.5 has college accurateness 67.7778% than ID3 and CART algorithm. Model’s True Positive amount for chic Abort is aerial 0.786 for ID3 and C4.5 which agency it will auspiciously analyze the abort students. This abstraction will be accessible for those acceptance that charge appropriate absorption from teachers.

Manpreet Singh Bhullar, Amritpal Kaur [10] (2012) accept taken abstracts set of 1892 acceptance from assorted colleges for apprentice achievement anticipation and evaluation. J48 algorithm was called for appraisal appliance 10 bend cantankerous validation. Success amount of J48 algorithm was 77.74%. In this way it will be accessible in anecdotic anemic acceptance so that agents can advice them afore failure.

Mrinal Pandey, Vivek Kumar Sharma [4] (Jan. 2013) compared J48, Simple Cart, Reptree and NB timberline algorithms for admiration achievement of engineering students. They accept taken abstracts of 524 acceptance for 10 bend cantankerous validation and 178 acceptance for allotment breach method. It has been begin that J48 accommodation timberline algorithm accomplished college accurateness 80.15% appliance 10 bend cantankerous validation method. By appliance allotment breach adjustment college accurateness 82.58% is accomplished by J48 algorithm. From this allegory it has been begin that J48 performs best than alternative algorithms in both the cases. J48 accommodation timberline algorithm will be advantageous for agents in convalescent achievement of anemic students.

Anuja Priyam, Abhijeet, Rahul Gupta, Anju Rathee, and Saurabh Srivastava [12] (June 2013) compared ID3, C4.5 and CART accommodation timberline algorithms on the base of acceptance data. Appraisal was performed appliance 10 bend cantankerous validation method. It shows that the CART algorithm has college accurateness 56.2500%. Model’s True Positive amount for chic Abort is aerial 0.786 for ID3 and C4.5 which agency it will auspiciously analyze the abort students. So this archetypal will advice agents in abbreviation abortion rates.

Ramanathan L, Saksham Dhanda, Suresh Kumar D [14] (June-July 2013) performed assay on 50 acceptance data. They were acclimated axis bayes, J48 and proposed algorithm (Weighted ID3) for evaluation. It shows that WID3 has college accurateness 93% than J48 and axis bayes. In approaching you can fabricated user affable software appliance WID3 which will be actual accessible for teachers.

Kalpesh Adhatrao, Aditya Gaykar, Amiraj Dhawan, Rohit Jha and Vipul Honrao [7] (September 2013) performed assay on abstracts set of 182 acceptance appliance ID3 and C4.5 accommodation timberline algorithms. Back they performed aggregate appraisal on abstracts set of 173 acceptance both algorithms accept aforementioned accurateness of 75.145% and back they performed atypical appraisal on abstracts set of 9 acceptance again both algorithms accept accurateness 77.778%. For 182 acceptance accurateness was about 75.257.

Mrs. M.S. Mythili, Dr. A.R.Mohamed Shanavas [9] ( Jan. 2014) compared J48, Accidental Forest, Multilayer Perception, IBI and accommodation timberline algorithms appliance abstracts set of 260 acceptance from assorted schools. 10 bend cantankerous validation was called for evaluation. It has been begin that Accidental Backwoods has college accurateness 89.23% and beneath beheading time amidst all alternative algorithms. This abstraction will be accessible for educational institutions.

Jyoti Namdeo, Naveenkumar Jayakumar [13] (Feb. 2014) calm 51 acceptance abstracts from MCA 2007 batch. Accommodation timberline algorithms acclimated in appraisal were Axis Bayes, Multilayer Perception, J48 and Accidental Forest. These algorithms were accomplished on 2007 accumulation abstracts and activated on 2008 accumulation data. Appraisal was performed appliance training, cantankerous validation, allotment breach and assay on 2008 data. After testing on 2008 abstracts it has been begin that axis bayes has college accurateness 31.57% amidst alternative algorithms but this accurateness is not according to requirement.

Azwa Abdul Aziz, Nor Hafieza IsmailandFadhilah Ahmad [8] (September 2014) conducted assay on 399 annal of acceptance appliance axis bayes, aphorism based and J48 accommodation timberline algorithm. They accept acclimated cantankerous validation and allotment breach adjustment for evaluation. In cantankerous validation 3, 5, 10 bend cantankerous validation was performed and in allotment breach adjustment training: testing 10:90, 20:80, 30:70, 40:60, 50:50, 40:60, 30:70, 20:80, 10:90 allotment breach were used. After allegory of 3 allocation algorithms it has been begin that aphorism based and J48 accommodation timberline algorithm has college accurateness 68.8%.

III. COMPARATIVE STUDY OF SURVEY

  1. Allegory of assay appointment based on altered parameters

Paper Name

Year of Publication

Size of Abstracts Set

(No. of students)

Algorithms Used

Test Options Used

Algorithm with College Accuracy

Accuracy (in %) of Algorithm

Performance Anticipation of Engineering Acceptance appliance Accommodation Trees

Dec. 2011

346

J48

Cross Validation

J48

60.46%

Data Mining: A Anticipation for Achievement Advance of Engineering Acceptance appliance Classification

2012

90

ID3

C4.5

CART

Cross Validation

C4.5

67.7778%

Use of Abstracts Mining in Apprenticeship Sector

2012

1892

J48

Cross Validation

J48

77.74%

A Accommodation Timberline Algorithm Pertaining to the Apprentice Achievement Assay and Prediction

Jan. 2013

524

J48

Simple cart

Reptree

NB tree

Cross Validation

J48

80.15%

178

J48

Simple cart

Reptree

NB tree

Percentage Split

J48

82.58%

Comparative Assay of Accommodation Timberline Allocation Algorithms

June 2013

____________

ID3

C4.5

CART

Cross Validation

CART

56.2500%

Predicting Students’ Achievement appliance Modified ID3 Algorithm

June-July 2013

50

Nave bayes

J48

Weighted ID3

____________

Weighted ID3

93%

Predicting Acceptance Achievement appliance ID3 and C4.5 Allocation Algorithms

September 2013

173

ID3

C4.5

for aggregate evaluation

Cross Validation

ID3

C4.5

75.145%

9

ID3

C4.5

for atypical evaluation

Cross Validation

ID3

C4.5

77.778%

An Assay of students’ achievement appliance allocation algorithms

Jan. 2014

260

J48

Random Forest

Multilayer Perception

IBI

Cross Validation

Random Forest

89.23%

Predicting Acceptance Achievement Appliance Abstracts Mining Technique with Rough Set Theory Concepts

Feb. 2014

51

J48

Random Forest

Multilayer Perception

Nave Bayes

Training

Cross Validation

Percentage Split

Test

Nave Bayes

31.57%

First Division Computer Science Students’ Bookish Performances Assay by Appliance Abstracts Mining Allocation Algorithms

September 2014

399

Nave Bayes

J48

Rule Based

Cross Validation

Percentage Split

J48

68.8%

IV. CONCLUSION

Educational abstracts mining’s (EDM) accent is accretion day by day as the student’s achievement anticipation and assay requirements are accretion for advance of student’s bookish performance. As accustomed aloft assorted authors accept implemented altered accommodation timberline algorithms: J48, accidental forest, multilayer perception, axis bayes, aphorism based, IBI, reptree, NB timberline and CART appliance altered abstracts sets. Some authors performed allegory of algorithms to acquisition out the best algorithm from them on the base of accuracy. The assay done in this cardboard shows that best apparently J48/C4.5 accommodation timberline algorithm is advised best algorithm in agreement of accurateness for altered abstracts sets. So it is bright from assay that J48 performs able-bodied for any admeasurement of abstracts set. This is the acumen abaft advanced use of J48 algorithm amidst all accommodation timberline algorithms.

Survey done in the area II will be accessible to assorted advisers that are alive in the acreage of student’s achievement anticipation and assay appliance accommodation timberline algorithms.

V. FUTURE WORK

For advance of any educational institute, student’s bookish achievement is capital contributor. If acceptance accomplish able-bodied academically again academy advance amount goes high. It is all-important in these canicule to focus on the student’s after-effects so there is a advanced ambit in this field. To access student’s performance, apprentice achievement anticipation and assay is used. For this purpose accommodation timberline algorithms are acclimated mainly. Assorted advisers accept done lot of analysis in this acreage by assuming appraisal appliance distinct algorithm or by comparing three or four algorithms.

In approaching advisers can enhance the analysis by comparing ample cardinal of algorithms appliance ample admeasurement abstracts sets. So there is a advanced ambit for advisers in this field.

ACKNOWLEDGMENT

First of all I accurate my sincerest debt of acknowledgment to the Almighty God who consistently supports me in my endeavors.

I would like to acknowledge Prof. Neena Madan for their advance and support. Then, I would like to acknowledge my ancestors and my friends. I am beholden to all those who helped me in one way or the alternative at every date of my work.

REFERENCES
  1. Nikita Jain, Vishal Srivastava, “Data mining techniques: A assay paper”, IJRET: International Journal of Analysis in Engineering and Technology, Volume: 02 Issue: 11, Nov-2013.
  2. Mrs. M.S. Mythili, Dr. A.R.Mohamed Shanavas, “An Assay of students’ achievement appliance allocation algorithms”, IOSR Journal of Computer Engineering, Volume 16, Issue 1, January 2014.
  3. Dr. Mohd Maqsood Ali, “Role of abstracts mining in apprenticeship sector”, International Journal of Computer Science and Mobile Computing Vol. 2, Issue. 4, April 2013.
  4. Mrinal Pandey, Vivek Kumar Sharma, “A Accommodation Timberline Algorithm Pertaining to the Apprentice Achievement Assay and Prediction”, International Journal of Computer Applications Volume 61, No.13, January 2013.
  5. Brijesh Kumar Baradwaj, Saurabh Pal, “Mining Educational Abstracts to Analyze Acceptance Performance”, International Journal of Advanced Computer Science and Applications, Vol. 2, No. 6, 2011.
  6. Surjeet Kumar Yadav, Saurabh Pal, “Data Mining: A Anticipation for Achievement Advance of Engineering Acceptance appliance Classification”, World of Computer Science and Advice Technology Journal Vol. 2, No. 2, 2012.
  7. Kalpesh Adhatrao, Aditya Gaykar, Amiraj Dhawan, Rohit Jha and Vipul Honrao, “Predicting Acceptance Achievement appliance ID3 and C4.5 Allocation Algorithms”, International Journal of Abstracts Mining & Ability Administration Action (IJDKP) Vol.3, No.5, September 2013.
  8. Azwa Abdul Aziz, Nor Hafieza IsmailandFadhilah Ahmad, “First Division Computer Science Students’ Bookish Performances Assay by Appliance Abstracts Mining Allocation Algorithms”, Proceeding of the International Conference on Artificial Intelligence and Computer Science(AICS 2014), September 2014.
  9. Mrs. M.S. Mythili, Dr. A.R.Mohamed Shanavas, “An Assay of students’ achievement appliance allocation algorithms”, IOSR Journal of Computer Engineering (IOSR-JCE) Volume 16, Issue 1, Jan. 2014.
  10. Manpreet Singh Bhullar, Amritpal Kaur, “Use of Abstracts Mining in Apprenticeship Sector”, Proceedings of the World Congress on Engineering and Computer Science (WCECS), San Francisco, USA, October 2012.
  11. R. R. Kabra, R. S. Bichkar, “Performance Anticipation of Engineering Acceptance appliance Accommodation Trees”, International Journal of Computer Applications Volume 36, No.11, December 2011.
  12. Anuja Priyam, Abhijeet, Rahul Gupta, Anju Rathee, and Saurabh Srivastava, “Comparative Assay of Accommodation Timberline Allocation Algorithms”, International Journal of Accepted Engineering and Technology, Volume 3, No .2, June 2013.
  13. [13] Jyoti Namdeo, Naveenkumar Jayakumar, “Predicting Acceptance Achievement Appliance Abstracts Mining Technique with Rough Set Theory Concepts”, International Journal of Advance Analysis in Computer Science and Administration Studies Volume 2, Issue 2, February 2014.
  14. [14] Ramanathan L, Saksham Dhanda, Suresh Kumar D, “Predicting Students’ Achievement appliance Modified ID3 Algorithm”, International Journal of Engineering and Technology (IJET) Volume 5, No. 3, Jun-Jul 2013.

Order a unique copy of this paper

550 words
We'll send you the first draft for approval by September 11, 2018 at 10:52 AM
Total price:
$26
Top Academic Writers Ready to Help
with Your Research Proposal
Live Chat+1(978) 822-0999EmailWhatsApp

Order your essay today and save 20% with the discount code COURSEGUY