arXiv subjects

Aditya Ghose

Publications and source records attributed to Aditya Ghose.

23 records · Page 2Linked to original sources

arXiv2016

A deep learning model for estimating story points

Although there has been substantial research in software analytics for effort estimation in traditional software projects, little work has been done for estimation in agile projects, especially estimating user stories or issues. Story points are the most common unit of measure used for estimating the effort involved in implementing a user story or resolving an issue. In this paper, we offer for the \emph{first} time a comprehensive dataset for story points-based estimation that contains 23,313 issues from 16 open source projects. We also propose a prediction model for estimating story points based on a novel combination of two powerful deep learning architectures: long short-term memory and recurrent highway network. Our prediction system is \emph{end-to-end} trainable from raw input data to prediction outcomes without any manual feature engineering. An empirical evaluation demonstrates that our approach consistently outperforms three common effort estimation baselines and two alternatives in both Mean Absolute Error and the Standardized Accuracy.

cs.SE↗

arXiv2016

DeepSoft: A vision for a deep model of software

Although software analytics has experienced rapid growth as a research area, it has not yet reached its full potential for wide industrial adoption. Most of the existing work in software analytics still relies heavily on costly manual feature engineering processes, and they mainly address the traditional classification problems, as opposed to predicting future events. We present a vision for \emph{DeepSoft}, an \emph{end-to-end} generic framework for modeling software and its development process to predict future risks and recommend interventions. DeepSoft, partly inspired by human memory, is built upon the powerful deep learning-based Long Short Term Memory architecture that is capable of learning long-term temporal dependencies that occur in software evolution. Such deep learned patterns of software can be used to address a range of challenging problems such as code and task recommendation and prediction. DeepSoft provides a new approach for research into modeling of source code, risk prediction and mitigation, developer modeling, and automatically generating code patches from bug reports.

cs.SE↗

arXiv2015

Extracting State Transition Models from i* Models

i* models are inherently sequence agnostic. There is an immediate need to bridge the gap between such a sequence agnostic model and an industry implemented process modelling standard like Business Process Modelling Notation (BPMN). This work is an attempt to build State Transition Models from i* models. In this paper, we first spell out the Naive Algorithm formally, which is on the lines of Formal Tropos. We demonstrate how the growth of the State Transition Model Space can be mapped to the problem of finding the number of possible paths between the Least Upper Bound (LUB) and the Greatest Lower Bound (GLB) of a k-dimensional hypercube Lattice structure. We formally present the mathematics for doing a quantitative analysis of the space growth. The Naive Algorithm has its main drawback in the hyperexponential explosion caused in the State Transition Model space. This is identified and the Semantic Implosion Algorithm is proposed which exploits the temporal information embedded within the i* model of an enterprise to reduce the rate of growth of the State Transition Model space. A comparative quantitative analysis between the two approaches concludes the superiority of the Semantic Implosion Algorithm.

cs.SE↗

arXiv2014

Towards rational and minimal change propagation in model evolution

A critical issue in the evolution of software models is change propagation: given a primary change that is made to a model in order to meet a new or changed requirement, what additional secondary changes are needed to maintain consistency within the model, and between the model and other models in the system? In practice, there are many ways of propagating changes to fix a given inconsistency, and how to justify and automate the selection between such change options remains a critical challenge. In this paper, we propose a number of postulates, inspired by the mature belief revision theory, that a change propagation process should satisfy to be considered rational and minimal. Such postulates enable us to reason about selecting alternative change options, and consequently to develop a machinery that automatically performs this task. We further argue that a possible implementation of such a change propagation process can be considered as a classical state space search in which each state represents a snapshot of the model in the process. This view naturally reflects the cascading nature of change propagation, where each change can require further changes to be made.

cs.SE↗

arXiv2002

Iterated revision and the axiom of recovery: a unified treatment via epistemic states

The axiom of recovery, while capturing a central intuition regarding belief change, has been the source of much controversy. We argue briefly against putative counterexamples to the axiom--while agreeing that some of their insight deserves to be preserved--and present additional recovery-like axioms in a framework that uses epistemic states, which encode preferences, as the object of revisions. This provides a framework in which iterated revision becomes possible and makes explicit the connection between iterated belief change and the axiom of recovery. We provide a representation theorem that connects the semantic conditions that we impose on iterated revision and the additional syntactical properties mentioned. We also show some interesting similarities between our framework and that of Darwiche-Pearl. In particular, we show that the intuitions underlying the controversial (C2) postulate are captured by the recovery axiom and our recovery-like postulates (the latter can be seen as weakenings of (C2).

cs.AI↗