scholarly journals An Intellectual Approach to Design Personal Study Plan via Machine Learning

2020 ◽  
Author(s):  
Shiyuan Zhang ◽  
Evan Gunnell ◽  
Marisabel Chang ◽  
Yu Sun
Keyword(s):  
Machine Learning ◽  
Test Scores ◽  
Educational Software ◽  
Cross Validation ◽  
Standardized Test ◽  
Standardized Test Scores ◽  
Validation Score ◽  
Specific Learning ◽  
Study Plan ◽  
Machine Learning Models

As more students are required to have standardized test scores to enter higher education, developing vocabulary becomes essential for achieving ideal scores. Each individual has his or her own study style that maximizes the efficiency, and there are various approaches to memorize. However, it is difficult to find a specific learning method that fits the best to a person. This paper designs a tool to customize personal study plans based on clients’ different habits including difficulty distribution, difficulty order of learning words, and the types of vocabulary. We applied our application to educational software and conducted a quantitative evaluation of the approach via three types of machine learning models. By calculating cross-validation scores, we evaluated the accuracy of each model and discovered the best model that returns the most accurate predictions. The results reveal that linear regression has the highest cross validation score, and it can provide the most efficient personal study plans.

scholarly journals Combining Outcome-Based and Preference-Based Matching: A Constrained Priority Mechanism

2021 ◽  
pp. 1-24
Author(s):  
Avidit Acharya ◽  
Kirk Bansak ◽  
Jens Hainmueller
Keyword(s):  
Machine Learning ◽  
Host Country ◽  
Real World ◽  
Test Scores ◽  
Standardized Test ◽  
Market Design ◽  
Standardized Test Scores ◽  
Real World Data ◽  
Refugee Families ◽  
Strategy Proof

Abstract We introduce a constrained priority mechanism that combines outcome-based matching from machine learning with preference-based allocation schemes common in market design. Using real-world data, we illustrate how our mechanism could be applied to the assignment of refugee families to host country locations, and kindergarteners to schools. Our mechanism allows a planner to first specify a threshold $\bar g$ for the minimum acceptable average outcome score that should be achieved by the assignment. In the refugee matching context, this score corresponds to the probability of employment, whereas in the student assignment context, it corresponds to standardized test scores. The mechanism is a priority mechanism that considers both outcomes and preferences by assigning agents (refugee families and students) based on their preferences, but subject to meeting the planner’s specified threshold. The mechanism is both strategy-proof and constrained efficient in that it always generates a matching that is not Pareto dominated by any other matching that respects the planner’s threshold.

scholarly journals Development of Machine Learning Models to Predict Compressed Sward Height in Walloon Pastures Based on Sentinel-1, Sentinel-2 and Meteorological Data Using Multiple Data Transformations

2021 ◽  
Vol 13 (3) ◽  
pp. 408
Author(s):  
Charles Nickmilder ◽  
Anthony Tedde ◽  
Isabelle Dufrasne ◽  
Françoise Lessire ◽  
Bernard Tychon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Support System ◽  
Cross Validation ◽  
Learning Models ◽  
Data Transformations ◽  
Independent Validation ◽  
Sward Height ◽  
Machine Learning Models ◽  
Sentinel 2

Accurate information about the available standing biomass on pastures is critical for the adequate management of grazing and its promotion to farmers. In this paper, machine learning models are developed to predict available biomass expressed as compressed sward height (CSH) from readily accessible meteorological, optical (Sentinel-2) and radar satellite data (Sentinel-1). This study assumed that combining heterogeneous data sources, data transformations and machine learning methods would improve the robustness and the accuracy of the developed models. A total of 72,795 records of CSH with a spatial positioning, collected in 2018 and 2019, were used and aggregated according to a pixel-like pattern. The resulting dataset was split into a training one with 11,625 pixellated records and an independent validation one with 4952 pixellated records. The models were trained with a 19-fold cross-validation. A wide range of performances was observed (with mean root mean square error (RMSE) of cross-validation ranging from 22.84 mm of CSH to infinite-like values), and the four best-performing models were a cubist, a glmnet, a neural network and a random forest. These models had an RMSE of independent validation lower than 20 mm of CSH at the pixel-level. To simulate the behavior of the model in a decision support system, performances at the paddock level were also studied. These were computed according to two scenarios: either the predictions were made at a sub-parcel level and then aggregated, or the data were aggregated at the parcel level and the predictions were made for these aggregated data. The results obtained in this study were more accurate than those found in the literature concerning pasture budgeting and grassland biomass evaluation. The training of the 124 models resulting from the described framework was part of the realization of a decision support system to help farmers in their daily decision making.

Predicting academic success for students of color within STEM majors

2016 ◽  
Vol 10 (2) ◽  
pp. 124-134 ◽  
Author(s):  
John Gipson
Keyword(s):  
High School ◽  
Students Of Color ◽  
Test Scores ◽  
College Success ◽  
Standardized Test ◽  
Cumulative Effect ◽  
Standardized Test Scores ◽  
Content Type ◽  
College Gpa ◽  
High School Gpa

Purpose The aim of this study is to determine what pre-college characteristics predict college success for students of color enrolled within science, technology, engineering and mathematics programs, as measured by cumulative grade point average (GPA) after three years of initial enrollment. Design/methodology/approach To increase the generalizability by avoiding a single-year focus, the sample includes 954 first-year students entering one predominantly White research university during Fall 2010, Fall 2011 and Fall 2012 (Allen and Bir, 2011); GPAs were collected following three years of initial enrollment. IBM statistical package for the social sciences (SPSS) Statistics 22 was utilized to conduct correlation and multiple linear regression analyses. Findings Within all conditional models, after controlling for multiple variables, the number of advanced placement (AP) credits, standardized test scores and specific type of high school GPA were significantly related to cumulative college GPA after three years of enrollment. However, when multiple forms of high school GPA were included within a full model, only the number of AP credits and standardized test scores remained statistically related to cumulative college GPA. Further, high school core GPA is more strongly correlated with cumulative college GPA after three years of enrollment than overall high school GPA, high school science GPA and high school mathematics GPA. Originality/value This study adds to prior research by identifying that high school core GPA is an important predictor of college success and that the cumulative effect of enrollment within AP credits may be more beneficial than the cumulative effect of involvement within dual enrollment courses.

Turning Standardized Test Scores into a Tool for Improving Teaching and Learning

2000 ◽  
Vol 35 (3) ◽  
pp. 356-384 ◽  
Author(s):  
Jie-Qi Chen ◽  
Renee Salahuddin ◽  
Patricia Horsch ◽  
Suzanne L. Wagner
Keyword(s):  
Test Scores ◽  
Teaching And Learning ◽  
Standardized Test ◽  
Standardized Test Scores ◽  
Improving Teaching And Learning

Predicting success in teacher education: Revisiting the influence of high school GPA, admission, and standardized test scores on academic and licensure performance

2020 ◽  
Vol 10 (2) ◽  
pp. 1-17
Author(s):  
Apler J. Bansiong ◽  
Janet Lynn M. Balagtey
Keyword(s):  
High School ◽  
Teacher Education ◽  
Grade Point Average ◽  
Test Scores ◽  
Standardized Test ◽  
Standardized Test Scores ◽  
Degree Programs ◽  
Licensure Examination ◽  
Grade Point ◽  
Admission Variables

This predictive study explored the influence of three admission variables on the college grade point average (CGPA), and licensure examination ratings of the 2015 teacher education graduates in a state-run university in Northern Philippines. The admission variables were high school grade point average (HSGPA), admission test (IQ) scores, and standardized test (General Scholastic Aptitude - GSA) scores. The participants were from two degree programs – Bachelor in Elementary Education (BEE) and Bachelor in Secondary education (BSE). The results showed that the graduates’ overall HSGPA were in the proficient level, while their admission and standardized test scores were average. Meanwhile, their mean licensure examination ratings were satisfactory, with high (BEE – 80.29%) and very high (BSE – 93.33%) passing rates. In both degree programs, all entry variables were significantly correlated and linearly associated with the CGPAs and licensure examination ratings of the participants. These entry variables were also linearly associated with the specific area GPAs and licensure ratings, except in the specialization area (for BSE). Finally, in both degrees, CGPA and licensure examination ratings were best predicted by HSGPA and standardized test scores, respectively. The implications of these findings on admission policies are herein discussed.

Association of Maternal Antidepressant Prescription During Pregnancy With Standardized Test Scores of Danish School-aged Children

JAMA ◽  
2021 ◽  
Vol 326 (17) ◽  
pp. 1725
Author(s):  
Jakob Christensen ◽  
Betina B. Trabjerg ◽  
Yuelian Sun ◽  
Julie Werenberg Dreier
Keyword(s):  
Test Scores ◽  
Standardized Test ◽  
Standardized Test Scores ◽  
School Aged Children ◽  
Antidepressant Prescription ◽  
Danish School
Sign in / Sign up

Export Citation Format

Share Document