Zachary A. Pardos, Ph.D. 
I've started as faculty at UCBerkeley (pr) Previously: Postdoctoral Associate ALFA Lab  CSAIL, MIT Email: pardos at mit dot edu [google scholar  ms academic  CV] Major: Computer Science Degree status: Defended Ph.D. thesis on 4262012 Research: Learning Analytics, Educational Data Mining, Machine Learning, Bayesian Networks Graduated: May, 2012 
2010: 
Pardos, Z. A., Heffernan, N. T., Anderson, B., Heffernan, C. (2010) Using FineGrained Skill Models to Fit Student Performance with Bayesian Networks. In C. Romero, S. Ventura, S. R. Viola, M. Pechenizkiy and R. S. J. Baker (Eds.) Handbook of Educational Data Mining. CRC Press, pp. 417426.  CRC 
2012: 
Pardos, Z.A., Gowda, S. M., Baker, R. S.J.D., Heffernan, N. T., The Sum is Greater than the Parts: Ensembling Models of Student Knowledge in Educational Software. ACM SIGKDD Explorations, 13(2)  PDF 
2011: 2011: 
Pardos, Z.A., Heffernan, N. T.: Using
HMMs and bagged decision trees to leverage rich features of user and
skill from an intelligent tutoring system dataset. To
appear in the Journal
of Machine Learning
Research W & CP, In Press  PDF
(prepress) Pardos, Z.A., Dailey, M. & Heffernan, N. (2011) Learning what works in ITS from nontraditional randomized controlled trial data. The International Journal of Artificial Intelligence in Education, 21(1):4763.  IJAIED 
2007:  Razzaq,
L., Heffernan, N.T., Feng, M., Pardos, Z.A. (2007) Developing
FineGrained Transfer Models in the ASSISTment System. Journal of Technology,
Instruction, Cognition, and Learning, Vol. 5. Number 3.
Old City Publishing, Philadelphia, PA. 2007. pp. 289304. 
TBD: TBD: TBD: 
Trivedi S, Pardos Z. A., Heffernan N. T., "The Utility of Clustering in Prediction Tasks”, IEEE Transactions on Systems, Man and Cybernetics, Part B. (Under Review) Trivedi S, Pardos Z. A., Sárközy G. N., Heffernan N. T., “Out of Sample Extensions to Spectral Clustering”, Statistics and Computing, Springer. (In Preparation) Pardos, Z. A., Heffernan, N. T. Determining the Significance of Item Order . Journal of Educational Data Mining. (Under Review) 
2013: 2013: 2013: 
A Spectral Learning Approach to Knowledge Tracing  Best student
paper winner  EDM  PDF Adapting Bayesian Knowledge Tracing to a Massive Open Online Course in edX  Best overall paper nominated  EDM  PDF Affective states and state tests: Investigating how affect throughout the school year predicts end of year learning outcomes  LAK  PDF 
2012: 2012: 2012: 
Tutor Modeling vs. Student Modeling  FLAIRS  PDF Content learning analysis using the momentbymoment learning detector  ITS  PDF CoClustering by Bipartite Spectral Graph Partitioning for OutofTutor Prediction  EDM  PDF 
2011: 2011: 2011: 2011: 2011: 2011: 2011: 
KTIDEM: Introducing Item Difficulty to the Knowledge
Tracing Model  UMAP
 PDF Ensembling Predictions of Student Knowledge within Intelligent Tutoring Systems  UMAP  PDF Clustering Students to Generate an Ensemble to Improve Standard Test Score Prediction  AIED  PDF Less is More: Improving the Speed and Prediction Power of Knowledge Tracing by Using Less Data  EDM  PDF Spectral Clustering in Educational Data Mining  EDM  PDF Does Time Matter? Modeling the Effect of Time with Bayesian Knowledge Tracing  EDM  PDF Ensembling Predictions of Student PostTest Scores for an Intelligent Tutoring System  EDM  PDF 
2010: 2010: 2010: 
Navigating the parameter space of Bayesian Knowledge Tracing models 
EDM  PDF,
Presentation

WPI  Poster
Modeling individualization in a bayesian networks implementation of knowledge tracing  UMAP  PDF Learning what works in ITS from nontraditional randomized controlled trial data  ITS  PDF 
2009: 2009: 
Detecting the learning value of items in a randomized problem set 
AIED  PDF Determining the significance of item order in randomized problem sets  EDM  PDF 
2008:  The composition effect: conjunctive or compensatory? An analysis of multiskill math questions in ITS  EDM  PDF 
2013: 2013: 
EDSciDB: Developing standards and backend support for MOOC Data Science
(Accepted)  moocshop@AIED Towards Moment of Learning Accuracy (Accepted)  Simulated Learners@AIED 
2012: 2012: 2012: 2012: 2012: 
Towards Data Driven Model Improvement  FLAIRS  PDF Knowledge Component Suggestion for Untagged Content in an Intelligent Tutoring System  ITS  PDF Clustered Knowledge Tracing  ITS  PDF The real world significance of performance prediction  EDM  PDF Investigating Practice Schedules of Multiple Fraction Representations Using Knowledge Tracing Based Learning Analysis Techniques  EDM  PDF 
2011: 2011: 2011: 2011: 
The Sum is Greater than the Parts: Ensembling Student Knowledge Models in ASSISTments  KDD
 PDF Response Tabling  A simple and practical complement to Knowledge Tracing  KDD  PDF An Analysis of Response Time Data for Improving Student Performance Prediction  KDD  PDF Establishing the value of dynamic assessment in an online tutoring system  EDM  PDF 
2008:  Effective skill assessment
using expectation maximization in a
multi network temporal Bayesian network  ITS  PDF 
2007: 2007: 
Analyzing finegrained
skill models using Bayesian and mixed
effect methods  AIED  PDF, Poster The effect of model granularity on student performance prediction using bayesian networks  UM  PDF, 5page, Poster 
2006:  Using finegrained skill models to fit student performance with Bayesian networks  ITS  PDF 
2010: 2010: 
Dataset of student
responses to 42 problem sets in The ASSISTment System  download
 analyzed in this paper: PDF
Temporal Bayes Net Experimenter for MATLAB  download  requires: BNT 
