Contrastive Explanations for Large Errors in Retail Forecasting Predictions through Monte Carlo Simulations

07/17/2019
by   Ana Lucic, et al.
0

At Ahold Delhaize, there is an interest in using more complex machine learning techniques for sales forecasting. It is difficult to convince analysts, along with their superiors, to adopt these techniques since the models are considered to be 'black boxes,' even if they perform better than current models in use. We aim to explore the impact of contrastive explanations about large errors on users' attitudes towards a 'black-box' model. In this work, we make two contributions. The first is an algorithm, Monte Carlo Bounds for Reasonable Predictions (MC-BRP). Given a large error, MC-BRP determines (1) feature values that would result in a reasonable prediction, and (2) general trends between each feature and the target, based on Monte Carlo simulations. The second contribution is the evaluation of MC-BRP along with its outcomes, which has both objective and subjective components. We evaluate on a real dataset with real users from Ahold Delhaize by conducting a user study to determine if explanations generated by MC-BRP help users understand why a prediction results in a large error, and if this promotes trust in an automatically-learned model. The study shows that users are able to answer objective questions about the model's predictions with overall 81.7 when provided with these contrastive explanations. We also show that users who saw MC-BRP explanations understand why the model makes large errors in predictions significantly more than users in the control group.

READ FULL TEXT
research
02/09/2023

Efficient Propagation of Uncertainty via Reordering Monte Carlo Samples

Uncertainty analysis in the outcomes of model predictions is a key eleme...
research
03/23/2021

Efficiently Answering Durability Prediction Queries

We consider a class of queries called durability prediction queries that...
research
05/09/2019

On the Efficacy of Monte Carlo Implementation of CAVI

In Variational Inference (VI), coordinate-ascent and gradient-based appr...
research
04/04/2022

Slope stability predictions on spatially variable random fields using machine learning surrogate models

Random field Monte Carlo (MC) reliability analysis is a robust stochasti...
research
09/24/2021

MLIMC: Machine learning-based implicit-solvent Monte Carlo

Monte Carlo (MC) methods are important computational tools for molecular...
research
03/12/2021

Reptile: Aggregation-level Explanations for Hierarchical Data

Recent query explanation systems help users understand anomalies in aggr...
research
08/01/2020

Contrastive Explanations in Neural Networks

Visual explanations are logical arguments based on visual features that ...

Please sign up or login with your details

Forgot password? Click here to reset