skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Using Machine Learning and Data Analysis to Improve Customer Acquisition and Marketing in Residential Solar

Abstract

High customer acquisition costs remain a persistent challenge in the U.S. residential solar industry. Effective customer acquisition in the residential solar market is increasingly achieved with the help of data analysis and machine learning, whether that means more targeted advertising, understanding customer motivations, or responding to competitors. New research by the National Renewable Energy Laboratory, Sandia National Laboratories, Vanderbilt University, University of Pennsylvania, and the California Center for Sustainable Energy and funded through the U.S. Department of Energy's Solar Energy Evolution and Diffusion (SEEDS) program demonstrates novel computational methods that can help drive down costs in the residential solar industry.

Authors:
 [1]
  1. National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Publication Date:
Research Org.:
National Renewable Energy Lab. (NREL), Golden, CO (United States)
Sponsoring Org.:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Solar Energy Technologies Office (EE-4S)
OSTI Identifier:
1402560
Report Number(s):
NREL/FS-6A20-70077
DOE Contract Number:
AC36-08GO28308
Country of Publication:
United States
Language:
English
Subject:
29 ENERGY PLANNING, POLICY, AND ECONOMY; SEEDS; Solar Energy Evolution and Diffusion; machine learning; data analysis; soft costs; solar soft costs; balance of system; solar balance of system

Citation Formats

Sigrin, Benjamin O. Using Machine Learning and Data Analysis to Improve Customer Acquisition and Marketing in Residential Solar. United States: N. p., 2017. Web.
Sigrin, Benjamin O. Using Machine Learning and Data Analysis to Improve Customer Acquisition and Marketing in Residential Solar. United States.
Sigrin, Benjamin O. 2017. "Using Machine Learning and Data Analysis to Improve Customer Acquisition and Marketing in Residential Solar". United States. doi:. https://www.osti.gov/servlets/purl/1402560.
@article{osti_1402560,
title = {Using Machine Learning and Data Analysis to Improve Customer Acquisition and Marketing in Residential Solar},
author = {Sigrin, Benjamin O},
abstractNote = {High customer acquisition costs remain a persistent challenge in the U.S. residential solar industry. Effective customer acquisition in the residential solar market is increasingly achieved with the help of data analysis and machine learning, whether that means more targeted advertising, understanding customer motivations, or responding to competitors. New research by the National Renewable Energy Laboratory, Sandia National Laboratories, Vanderbilt University, University of Pennsylvania, and the California Center for Sustainable Energy and funded through the U.S. Department of Energy's Solar Energy Evolution and Diffusion (SEEDS) program demonstrates novel computational methods that can help drive down costs in the residential solar industry.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2017,
month =
}
  • The marketing and market acceptance components of HUD's Residential Solar Heating and Cooling Demonstration Program, designed to promote the development of a self-sustaining solar energy industry, are analyzed. The purposes of this report are to (1) describe the actual experiences of sectors and institutions involved in the market acceptance of solar houses and (2) identify and explore emerging trends in the characteristics, opinions, and actions of participants in the demonstration program. All findings are based on marketing interviews with program participants, with a market acceptance model used to guide analysis. Practical information relevant to the construction industry and solar manufacturersmore » is emphasized.« less
  • Solar homes were inspected and builders, buyers, and institutions involved in solar homes were interviewed to gather information about the marketability and acceptance of active residential solar energy. The study was conducted as part of the HUD Residential Solar Heating and Cooling Demonstration Program, which was designed to promote the development of a self - sustaining solar energy industry. Study participants include 138 builders, 276 buyers, and lending officers, municipal and county officials, utility representatives, and insurance agents involved with solar homes, as well as similar respondents involved with conventional homes. About 85 percent of the builders questioned expressed satisfactionmore » with their experience in the demonstration program. Their sales experience has been largely successful and their costs recoverable. They also like the minimal red tape and construction problems encountered in solar home building and the promotional and publicity advantages of the solar home. Houses constructed in the demonstration program are similar in style and offer the same amenities and features as new conventional housing in the same areas. Solar homebuyers are concerned mainly with such traditional home values as product quality and effective market location. Purchasers closely resemble buyers of similarly priced conventional houses and do not consider the solar energy system as the only or most important factor in the purchase decision. Interviews with institutional representatives reveal few existing financial, administrative, or legislative impediments to residential solar application. Insurance companies currently do not differentiate between solar and conventional homes and are mainly concerned that the system be properly constructed and installed. Findings strongly indicate that residential solar energy is being accepted in the marketplace. Figures, tables, footnotes, and a map are included.« less
  • We attempt to forecast M- and X-class solar flares using a machine-learning algorithm, called support vector machine (SVM), and four years of data from the Solar Dynamics Observatory's Helioseismic and Magnetic Imager, the first instrument to continuously map the full-disk photospheric vector magnetic field from space. Most flare forecasting efforts described in the literature use either line-of-sight magnetograms or a relatively small number of ground-based vector magnetograms. This is the first time a large data set of vector magnetograms has been used to forecast solar flares. We build a catalog of flaring and non-flaring active regions sampled from a databasemore » of 2071 active regions, comprised of 1.5 million active region patches of vector magnetic field data, and characterize each active region by 25 parameters. We then train and test the machine-learning algorithm and we estimate its performances using forecast verification metrics with an emphasis on the true skill statistic (TSS). We obtain relatively high TSS scores and overall predictive abilities. We surmise that this is partly due to fine-tuning the SVM for this purpose and also to an advantageous set of features that can only be calculated from vector magnetic field data. We also apply a feature selection algorithm to determine which of our 25 features are useful for discriminating between flaring and non-flaring active regions and conclude that only a handful are needed for good predictive abilities.« less
  • The identification of transcription units (TUs) encoded in a bacterial genome is essential to elucidation of transcriptional regulation of the organism. To gain a detailed understanding of the dynamically composed TU structures, we have used four strand-specific RNA-seq (ssRNA-seq) datasets collected under two experimental conditions to derive the genomic TU organization of Clostridium thermocellum using a machine-learning approach. Our method accurately predicted the genomic boundaries of individual TUs based on two sets of parameters measuring the RNA-seq expression patterns across the genome: expression-level continuity and variance. A total of 2590 distinct TUs are predicted based on the four RNA-seq datasets.more » Moreover, among the predicted TUs, 44% have multiple genes. We assessed our prediction method on an independent set of RNA-seq data with longer reads. The evaluation confirmed the high quality of the predicted TUs. Functional enrichment analyses on a selected subset of the predicted TUs revealed interesting biology. To demonstrate the generality of the prediction method, we have also applied the method to RNA-seq data collected on Escherichia coli and achieved high prediction accuracies. The TU prediction program named SeqTU is publicly available athttps://code.google.com/p/seqtu/. We expect that the predicted TUs can serve as the baseline information for studying transcriptional and post-transcriptional regulation in C. thermocellum and other bacteria.« less
  • Identification of transcription units (TUs) encoded in a bacterial genome is essential to elucidation of transcriptional regulation of the organism. To gain a detailed understanding of the dynamically composed TU structures, we have used four strand-specific RNA-seq (ssRNA-seq) datasets collected under two experimental conditions to derive the genomic TU organization of Clostridium thermocellum using a machine-learning approach. Our method accurately predicted the genomic boundaries of individual TUs based on two sets of parameters measuring the RNA-seq expression patterns across the genome: expression-level continuity and variance. A total of 2590 distinct TUs are predicted based on the four RNA-seq datasets. Amongmore » the predicted TUs, 44% have multiple genes. We assessed our prediction method on an independent set of RNA-seq data with longer reads. The evaluation confirmed the high quality of the predicted TUs. Functional enrichment analyses on a selected subset of the predicted TUs revealed interesting biology. To demonstrate the generality of the prediction method, we have also applied the method to RNA-seq data collected on Escherichia coli and achieved high prediction accuracies. The TU prediction program named SeqTU is publicly available at https://code.google.com/p/seqtu/. We expect that the predicted TUs can serve as the baseline information for studying transcriptional and post-transcriptional regulation in C. thermocellum and other bacteria.« less