Improving the expressiveness of black-box models for predicting student performance
نویسندگان
چکیده
Early prediction systems of student performance can be very useful to guide student learning. For a prediction model to be really useful as an effective aid for learning, it must provide tools to adequately interpret progress, to detect trends and behaviour patterns and to identify the causes of learning problems. White-box and black-box techniques have been described in literature to implement prediction models. White-box techniques require a priori models to explore, which make them easy to interpret but difficult to be generalized and unable to detect unexpected relationships between data. Black-box techniques are easier to generalize and suitable to discover unsuspected relationships but they are cryptic and difficult to be interpreted for most teachers. In this paper a black-box technique is proposed to take advantage of the power and versatility of these methods, while making some decisions about the input data and design of the classifier that provide a rich output data set. A set of graphical tools is also proposed to exploit the output information and provide a meaningful guide to teachers and students. From our experience, a set of tips about how to design a prediction system and the representation of the output information is also provided.
منابع مشابه
A study on the role of selective attention, vigilance and ambivalence over emotional expressiveness for predicting pain severity in patients with chronic musculoskeletal pains
Introduction: When there is a pain requiring focused clinical attention and is associated with emotional and functional disorders, it is called pain disorder. The present study aims to study the role of selective attention, vigilance and ambivalence over emotional expressiveness for predicting pain severity in patients with chronic musculoskeletal pains. Methods: The study population included 1...
متن کاملEvaluating Subunits Importance in Performance Measurement of Network Systems in Data Envelopment Analysis
In conventional DEA models, decision making units (DMUs) are generally assumed as a black-box while the performance of decision making sub-units (DMSUs) and their importance play crucial roles in analyzing the performance of systems which have internal processes. The present paper introduces an ideal network which have efficient processes and next purposes a new approach for evaluating importa...
متن کاملPerformance Evaluation of Supply Chain under Decentralized Organization Mechanism
Abstract Nowadays among many evaluation methods, data envelopment analysis has widely used to evaluate the relative performance of a set of Decision Making Units (DMUs). Data Envelopment Analysis (DEA(is a mathematical tool for evaluating the relative efficiency of a set Decision Making Units (DMUs), with multiple inputs and outputs. Traditional DEA models treat with each DMU as a “black box" t...
متن کاملThe overall efficiency and projection point in network DEA
Data Envelopment Analysis (DEA) is one of the best methods for measuring the efficiency and productivity of Decision Making Units (DMU). Evaluating the efficiency of DMUs which have two or several stages by using the conventional DEA models, is equal to consider them as black box. This method, omits the effect of intermediate measure on efficiency. Therefore, just the first network inputs and t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Computers in Human Behavior
دوره 72 شماره
صفحات -
تاریخ انتشار 2017