Predicting initial electricity demand in off-grid Tanzanian communities using customer survey data and machine learning models

2021 ◽  
Vol 62 ◽  
pp. 56-66
Author(s):  
Andrew Allee ◽  
Nathaniel J. Williams ◽  
Alexander Davis ◽  
Paulina Jaramillo
Keyword(s):  
Machine Learning ◽  
Survey Data ◽  
Electricity Demand ◽  
Learning Models ◽  
Customer Survey ◽  
Machine Learning Models

scholarly journals A Comparative Analysis of Machine Learning Models for the Prediction of Insurance Uptake in Kenya

Data ◽  
2021 ◽  
Vol 6 (11) ◽  
pp. 116
Author(s):  
Nelson Kemboi Yego ◽  
Juma Kasozi ◽  
Joseph Nkurunziza
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Phase I ◽  
Survey Data ◽  
Low Income ◽  
Random Forest Model ◽  
Learning Models ◽  
Forest Model ◽  
Learning Classifiers ◽  
Machine Learning Models

The role of insurance in financial inclusion and economic growth, in general, is immense and is increasingly being recognized. However, low uptake impedes the growth of the sector, hence the need for a model that robustly predicts insurance uptake among potential clients. This study undertook a two phase comparison of machine learning classifiers. Phase I had eight machine learning models compared for their performance in predicting the insurance uptake using 2016 Kenya FinAccessHousehold Survey data. Taking Phase I as a base in Phase II, random forest and XGBoost were compared with four deep learning classifiers using 2019 Kenya FinAccess Household Survey data. The random forest model trained on oversampled data showed the highest F1-score, accuracy, and precision. The area under the receiver operating characteristic curve was furthermore highest for random forest; hence, it could be construed as the most robust model for predicting the insurance uptake. Finally, the most important features in predicting insurance uptake as extracted from the random forest model were income, bank usage, and ability and willingness to support others. Hence, there is a need for a design and distribution of low income based products, and bancassurance could be said to be a plausible channel for the distribution of insurance products.

Assessing consumer buy and pay preferences for labeled food products with statistical and machine learning methods

2021 ◽  
Author(s):  
Yike Shen ◽  
Joseph A. Hamm ◽  
Feng Gao ◽  
Elliot T. Ryser ◽  
Wei Zhang
Keyword(s):  
Machine Learning ◽  
Survey Data ◽  
Food Production ◽  
Prediction Accuracy ◽  
Environmental Science ◽  
Food Products ◽  
Grocery Stores ◽  
Learning Models ◽  
Production Practices ◽  
Machine Learning Models

Food labeling is one approach to encourage safe, healthy, and sustainable dietary practices. Consumer buy and pay preferences to specially labeled food products (e.g., USDA Organic, Raised Without Antibiotics, and Locally Raised) may promote the adoption of associated production practices by food producers. Thus, it is important to understand how consumer buy and pay preferences for specially labeled products vary with their demographics, food-relevant habits, and foodborne disease perceptions. Using both conventional statistical and novel machine learning models, this study analyzed Michigan State University Environmental Science and Policy Program annual survey data (2019) to characterize consumer buy and pay preferences regarding eight labels related to food production practices. Older consumer age was significantly associated with lower consumer willingness to pay more for labeled products. Participants who prefer to shop in non-conventional grocery stores were more willing to buy and pay more for labeled products. Our machine learning models provide a new approach for analyzing food safety and labeling survey data and produced adequate average prediction accuracy scores for all eight labels. The label, Raised Without Antibiotics, had the highest average prediction accuracy for consumer willingness to buy. Thus, the machine learning models may be used to analyze food survey data and help develop strategies for promoting healthy food production practices.

Improving XGBoost with Imagination Sampling

2020 ◽  
Vol 2 (1) ◽  
pp. 3-6
Author(s):  
Eric Holloway
Keyword(s):  
Machine Learning ◽  
General System ◽  
Learning Models ◽  
Starting Point ◽  
Machine Learning Models

Imagination Sampling is the usage of a person as an oracle for generating or improving machine learning models. Previous work demonstrated a general system for using Imagination Sampling for obtaining multibox models. Here, the possibility of importing such models as the starting point for further automatic enhancement is explored.

Epigenetic Target Prediction with Accurate Machine Learning Models

2021 ◽  
Author(s):  
Norberto Sánchez-Cruz ◽  
Jose L. Medina-Franco
Keyword(s):  
Machine Learning ◽  
Small Molecules ◽  
Predictive Models ◽  
Large Scale ◽  
Target Prediction ◽  
Quantitative Measure ◽  
Learning Models ◽  
Discovery Research ◽  
Drug Discovery Research ◽  
Machine Learning Models

<p>Epigenetic targets are a significant focus for drug discovery research, as demonstrated by the eight approved epigenetic drugs for treatment of cancer and the increasing availability of chemogenomic data related to epigenetics. This data represents a large amount of structure-activity relationships that has not been exploited thus far for the development of predictive models to support medicinal chemistry efforts. Herein, we report the first large-scale study of 26318 compounds with a quantitative measure of biological activity for 55 protein targets with epigenetic activity. Through a systematic comparison of machine learning models trained on molecular fingerprints of different design, we built predictive models with high accuracy for the epigenetic target profiling of small molecules. The models were thoroughly validated showing mean precisions up to 0.952 for the epigenetic target prediction task. Our results indicate that the herein reported models have considerable potential to identify small molecules with epigenetic activity. Therefore, our results were implemented as freely accessible and easy-to-use web application.</p>

Sign in / Sign up

Export Citation Format

Share Document