An Integrated Framework for Predicting Consumer Choice Through Modeling of Preference and Product Use Data

2017 ◽  
Author(s):  
Dipanjan D. Ghosh ◽  
Andrew Olewnik ◽  
Kemper E. Lewis
Keyword(s):  
Analytical Method ◽  
Consumer Choice ◽  
Latent Variables ◽  
Design Space ◽  
User Preferences ◽  
Model Parameters ◽  
Generation Process ◽  
Interaction Data ◽  
Empathic Design ◽  
Product Interaction

A critical task in product design is mapping information from consumer space to design space. Currently, this process is largely dependent on the designer to identify and map how psychological and consumer level factors relate to engineered product attributes. In this way, current methodologies lack provision to test a designer’s cognitive reasoning, which could introduce bias while mapping from consumer to design space. Cyber-Empathic Design is a novel framework where user-product interaction data is acquired using embedded sensors. To understand consumer perceptions about a particular product, a network of latent psychological constructs is used to form a causal model allowing designers to better understand user preferences. In this work, we extend this framework by integrating choice-based preference modeling to develop a Discrete Choice Analysis integrated Cyber-Empathic design framework (DCA-CED). We model user preferences and ultimately consumer choice by considering perceptions estimated by psychological latent variables and user-product interaction data. To demonstrate the effectiveness of the framework, a case study using a sensor integrated shoe design is presented where data to represent user demographics, sensor readings, and product choice is simulated. Using the DCA-CED method, the model parameters are recovered and compared with the original parameter values in the simulator. In addition, the ability of the framework to predict choice based on user product-interaction data is tested. The results show that the analytical method effectively captures the underlying data generation process thereby validating the proposed framework and the analytical method.

scholarly journals Cyber-Empathic Design: A Data Driven Framework for Product Design

2016 ◽  
Author(s):  
Dipanjan D. Ghosh ◽  
Junghan Kim ◽  
Andrew Olewnik ◽  
Arun Lakshmanan ◽  
Kemper E. Lewis
Keyword(s):  
Product Design ◽  
Structural Equation ◽  
Design Space ◽  
Equation Modeling ◽  
Design Decision ◽  
Interaction Data ◽  
Model Framework ◽  
Empathic Design ◽  
Product Interaction

One of the critical tasks in product design is to map information from the consumer space to the design space. Currently, this process is largely dependent on the designer to identify and map how psychological and consumer level factors relate to engineered product attributes. In this way current methodologies lack provision to test a designer’s cognitive reasoning and could therefore introduce bias while mapping from consumer to design space. Also, current dominant frameworks do not include user-product interaction data in design decision making and neither do they assist designers in understanding why a consumer has a particular perception about a product. This paper proposes a new framework — Cyber-Empathic Design — where user-product interaction data is acquired via embedded sensors in the products. To understand the motivations behind consumer perceptions, a network of latent constructs is used which forms a causal model framework. Structural Equation Modeling is used as the parameter estimation and hypothesis testing technique making the framework falsifiable in nature. To demonstrate the framework and demonstrate its effectiveness a case study of sensor integrated shoes is presented in this work, where two models are compared — one survey based and using the Cyber-Empathic framework model. It is shown that the Cyber-Empathic framework results in improved fit. The case study also demonstrates the technique to test a designers’ cognitive hypothesis.

scholarly journals Cyber-Empathic Design: A Data-Driven Framework for Product Design

2017 ◽  
Vol 139 (9) ◽  
Author(s):  
Dipanjan Ghosh ◽  
Andrew Olewnik ◽  
Kemper Lewis ◽  
Junghan Kim ◽  
Arun Lakshmanan
Keyword(s):  
Product Design ◽  
Structural Equation ◽  
Design Space ◽  
Equation Modeling ◽  
Design Decision ◽  
Interaction Data ◽  
Fit Indices ◽  
User Perceptions ◽  
Psychological Constructs ◽  
Product Interaction

A critical task in product design is mapping information from consumer to design space. Currently, this process largely depends on designers identifying and mapping psychological and consumer level factors to engineered attributes. In this way, current methodologies lack provision to test a designer's cognitive reasoning and could introduce bias when mapping from consumer to design space. In addition, current dominant frameworks do not include user–product interaction data in design decision making, nor do they assist designers in understanding why a consumer has a particular perception about a product. This paper proposes a framework—cyber-empathic (CE) design—where user–product interaction data are acquired using embedded sensors. To gain insight into consumer perceptions relative to product features, a network of psychological constructs is utilized. Structural equation modeling (SEM) is used as the parameter estimation and hypothesis testing technique, making the framework falsifiable in nature. To demonstrate effectiveness of the framework, a case study of sensor-integrated shoes is presented, where two models are compared—one survey-only and one using the cyber-empathic framework model. Covariance-based SEM (CB-SEM) is used to estimate the parameters and the fit indices. It is shown that the cyber-empathic framework results in improved fit over a survey-only SEM. This work demonstrates how low-level user–product interaction data can be used to understand and model user perceptions in a way that can support falsifiable design inference.

A GAMMA MOVING AVERAGE PROCESS FOR MODELLING DEPENDENCE ACROSS DEVELOPMENT YEARS IN RUN-OFF TRIANGLES

2020 ◽  
pp. 1-22
Author(s):  
Luis E. Nieto-Barajas ◽  
Rodrigo S. Targino
Keyword(s):  
Latent Variables ◽  
Moving Average ◽  
Real Data ◽  
Model Parameters ◽  
Average Process ◽  
Moving Average Process ◽  
Data Set ◽  
Run Off ◽  
Average Form ◽  
Reserve Estimates

ABSTRACT We propose a stochastic model for claims reserving that captures dependence along development years within a single triangle. This dependence is based on a gamma process with a moving average form of order $p \ge 0$ which is achieved through the use of poisson latent variables. We carry out Bayesian inference on model parameters and borrow strength across several triangles, coming from different lines of businesses or companies, through the use of hierarchical priors. We carry out a simulation study as well as a real data analysis. Results show that reserve estimates, for the real data set studied, are more accurate with our gamma dependence model as compared to the benchmark over-dispersed poisson that assumes independence.

scholarly journals Trajectory-User Linking via Variational AutoEncoder

2018 ◽  
Author(s):  
Fan Zhou ◽  
Qiang Gao ◽  
Goce Trajcevski ◽  
Kunpeng Zhang ◽  
Ting Zhong ◽  
...  
Keyword(s):  
Latent Variables ◽  
Large Scale ◽  
Human Mobility ◽  
Hierarchical Structures ◽  
High Dimensional ◽  
Generation Process ◽  
Mobility Patterns ◽  
Variational Autoencoder ◽  
Hidden States ◽  
Structural Semantics

Trajectory-User Linking (TUL) is an essential task in Geo-tagged social media (GTSM) applications, enabling personalized Point of Interest (POI) recommendation and activity identification. Existing works on mining mobility patterns often model trajectories using Markov Chains (MC) or recurrent neural networks (RNN) -- either assuming independence between non-adjacent locations or following a shallow generation process. However, most of them ignore the fact that human trajectories are often sparse, high-dimensional and may contain embedded hierarchical structures. We tackle the TUL problem with a semi-supervised learning framework, called TULVAE (TUL via Variational AutoEncoder), which learns the human mobility in a neural generative architecture with stochastic latent variables that span hidden states in RNN. TULVAE alleviates the data sparsity problem by leveraging large-scale unlabeled data and represents the hierarchical and structural semantics of trajectories with high-dimensional latent variables. Our experiments demonstrate that TULVAE improves efficiency and linking performance in real GTSM datasets, in comparison to existing methods.

scholarly journals The Impact of Employer Attitude to Green Commuting Plans on Reducing Car Driving: A Mixed Method Analysis

2014 ◽  
Vol 26 (2) ◽  
pp. 109-119 ◽  
Author(s):  
Chuan Ding ◽  
Chao Liu ◽  
Yaoyu Lin ◽  
Yaowu Wang
Keyword(s):  
Co2 Emissions ◽  
Mixed Method ◽  
Latent Variables ◽  
Choice Model ◽  
Mode Choice ◽  
Car Ownership ◽  
Simultaneous Estimation ◽  
Model Parameters ◽  
Employer Attitudes ◽  
The Impact

Reducing car trips and promoting green commuting modes are generally considered important solutions to reduce the increase of energy consumption and transportation CO2 emissions. One potential solution for alleviating transportation CO2 emissions has been to identify a role for the employer through green commuter programs. This paper offers an approach to assess the effects of employer attitudes towards green commuting plans on commuter mode choice and the intermediary role car ownership plays in the mode choice decision process. A mixed method which extends the traditional discrete choice model by incorporating latent variables and mediating variables with a structure equation model was used to better understand the commuter mode choice behaviour. The empirical data were selected from Washington-Baltimore Regional Household Travel Survey in 2007-2008, including all the trips from home to workplace during the morning hours. The model parameters were estimated using the simultaneous estimation approach and the integrated model turns out to be superior to the traditional multinomial logit (MNL) model accounting for the impact of employer attitudes towards green commuting. The direct and indirect effects of socio-demographic attributes and employer attitudes towards green commuting were estimated. Through the structural equation modelling with mediating variable, this approach confirmed the intermediary nature of car ownership in the choice process. The results found in this paper provide helpful information for transportation and planning policymakers to test the transportation and planning policies effects and encourage green commuting reducing transportation CO2 emissions.

Combining Non-Parametric and Parametric Models for Stable and Computationally Efficient Battery Health Estimation

2020 ◽  
Author(s):  
Antti Aitio ◽  
David Howey
Keyword(s):  
Latent Variables ◽  
Linear Time ◽  
Full Range ◽  
Real Life ◽  
Internal Resistance ◽  
State Of Charge ◽  
Parametric Models ◽  
Model Parameters ◽  
Battery Management ◽  
Resistance Change

Abstract Equivalent circuit models for batteries are commonly used in electric vehicle battery management systems to estimate state of charge and other important latent variables. They are computationally inexpensive, but suffer from a loss of accuracy over the full range of conditions that may be experienced in real-life. One reason for this is that the model parameters, such as internal resistance, change over the lifetime of the battery due to degradation. However, estimating long term changes is challenging, because parameters also change with state of charge and other variables. To address this, we modelled the internal resistance parameter as a function of state of charge and degradation using a Gaussian process (GP). This was performed computationally efficiently using an algorithm [1] that interprets a GP to be the solution of a linear time-invariant stochastic differential equation. As a result, inference of the posterior distribution of the GP scales as 𝒪(n) and can be implemented recursively using a Kalman filter.

scholarly journals Application of Design Space, Uncertainty, and Risk Profile Strategies to the Development and Validation of UPLC Method for the Characterization of Four Authorized Phosphodiesterase Type 5 Inhibitors to Combat Counterfeit Drugs

2020 ◽  
Vol 103 (3) ◽  
pp. 715-724
Author(s):  
Yassine Hameda Benchekroun ◽  
Miloud El Karbane ◽  
Bouchaib Ihssane ◽  
Hasnaa Haidara ◽  
Mohamed Azougagh ◽  
...  
Keyword(s):  
Analytical Method ◽  
Design Space ◽  
Ultra Performance Liquid Chromatography ◽  
Risk Profile ◽  
Tolerance Interval ◽  
Counterfeit Drugs ◽  
Phosphodiesterase Type 5 Inhibitors ◽  
Phosphodiesterase Type ◽  
Development And Validation

Abstract Background Counterfeit medicines are an increasing scourge that are difficult to identify and they have become industrialized and widespread through highly organized illegal channels. Objective This research aims to develop a robust method to determine four phosphodiesterase type-5 inhibitors in counterfeit drugs based on ultra-performance liquid chromatography. Method Experimental design methodology (DOE) and design space (DS) recommended by ICH Q8 were used side-by-side in the development phase to define the optimal parameters as well as the robustness of the chromatographic method. Moreover, both the uncertainty and risk profile derived from the β-content and γ-confidence tolerance interval were investigated during the validation phase to examine the performance of this method. Results Successful chromatographic results, in a high resolution between the four active ingredients and an optimal analysis time of less than 1.6 min, were achieved at the end of the optimization phase. In addition, validation results show a low risk of future measurements outside acceptance limits set at 5%. Conclusions Our procedure was successfully applied in the routine phase to identify 23 illicit formulations of an erectile dysfunction drug. Highlights An efficient method for the characterization of 4 authorized phosphodiesterase in less than 1.6 min was established. A DS approach was applied to test the performance of this analytical method during analytical development. A risk profile was then carried out to approve the validity of the analytical method through the uncertainty profile approach.

scholarly journals Variational Inference over Nonstationary Data Streams for Exponential Family Models

Mathematics ◽  
2020 ◽  
Vol 8 (11) ◽  
pp. 1942
Author(s):  
Andrés R. Masegosa ◽  
Darío Ramos-López ◽  
Antonio Salmerón ◽  
Helge Langseth ◽  
Thomas D. Nielsen
Keyword(s):  
Bayesian Inference ◽  
Variational Methods ◽  
Latent Variables ◽  
Exponential Family ◽  
Concept Drift ◽  
Variational Inference ◽  
Model Parameters ◽  
Time Step ◽  
Data Set ◽  
Family Models

In many modern data analysis problems, the available data is not static but, instead, comes in a streaming fashion. Performing Bayesian inference on a data stream is challenging for several reasons. First, it requires continuous model updating and the ability to handle a posterior distribution conditioned on an unbounded data set. Secondly, the underlying data distribution may drift from one time step to another, and the classic i.i.d. (independent and identically distributed), or data exchangeability assumption does not hold anymore. In this paper, we present an approximate Bayesian inference approach using variational methods that addresses these issues for conjugate exponential family models with latent variables. Our proposal makes use of a novel scheme based on hierarchical priors to explicitly model temporal changes of the model parameters. We show how this approach induces an exponential forgetting mechanism with adaptive forgetting rates. The method is able to capture the smoothness of the concept drift, ranging from no drift to abrupt drift. The proposed variational inference scheme maintains the computational efficiency of variational methods over conjugate models, which is critical in streaming settings. The approach is validated on four different domains (energy, finance, geolocation, and text) using four real-world data sets.

Sign in / Sign up

Export Citation Format

Share Document