California Housing Research Articles

Appealing for Local Control and Spatial Inequality: Reforming Governance and Development Rationalities in Southern California

Several limitations have thwarted the implementation of California housing law for over fifty years. This paper sheds light on the evolution of municipal-state relations at a period of reform by analyzing the contentious implementation of state housing law in Orange County, California, a region of concentrated affluence. Systemic privilege has historically allowed some jurisdictions to influence decision-making at higher levels, skewing housing policy and planning outcomes. Nonetheless, and despite contention between different government levels and localities, the leverage of reactionary local politics is weakening.

Variable selection of nonparametric spatial autoregressive models via deep learning

With the development of deep learning techniques, the application of neural networks to statistical inference has dramatically increased in popularity. In this paper, we extend the deep neural network-based variable selection method to nonparametric spatial autoregressive models. Our approach incorporates feature selection and parameter learning by introducing Lasso penalties in a residual network structure with spatial effects. We transform the problem into a constrained optimization task, where optimizing an objective function with constraints. Without specifying sparsity, we are also able to obtain a specific set of selected variables. The performance of the method with finite samples is demonstrated through an extensive Monte Carlo simulation study. Finally, we apply the method to California housing price data, further validating its superiority in terms of variable selection and predictive performance.

Community-Led Solutions: How Local Organizing Committees Drive Change for Housing and Health Equity in California’s Central Valley

In this research brief, we describe how the HOPe Lab (UC Merced), Faith in the Valley (Fresno), and Cultiva Central Valley (Merced) are collaborating to address housing-related disparities within California’s culturally diverse Central Valley. Focused on the transformative role of Local Organizing Committees (LOCs), our research employs an anti-racist research praxis to actively engage residents, enhance leadership capacity, and foster communication between residents and elected officials. Drawing on several theory-of-change statements and the practical insights gained from “field experts” carrying out ongoing initiatives, this report explores the positive impact of LOCs on meaningful community involvement, empowerment, engagement, accountability, and policy changes.

Meaningful Action: Evaluating Local Government Plans to Affirmatively Further Fair Housing in California

A 2018 California law requires local governments to affirmatively further fair housing (AFFH) in their General Plan’s housing element. This paper examines how eight municipalities reacted to this requirement in three areas of their 2021 plans: the analysis of fair housing issues, proposed fair housing programs, and the location of sites identified for low-income housing development. We consider whether these cities’ over 200 fair housing programs are meaningful actions by evaluating their potential impact, and measure the distribution of proposed sites for new low-income housing across neighborhoods. The cities created many new programs in response to the mandate; however, most programs do not meaningfully advance fair housing goals. Moreover, most cities do not modify land-use plans to allow affordable housing in affluent neighborhoods. Additionally, we find a mismatch in the plans. The affluent, majority-white cities that developed more meaningful fair housing programs continued to concentrate sites for affordable housing in their least affluent neighborhoods. Our analysis of potential program impact allows us to identify AFFH oversight challenges and make recommendations for AFFH guidelines. We focus on California, but the research is relevant to federal AFFH implementation and raises questions about how to best advance fair housing goals.

Improved Regression Analysis with Ensemble Pipeline Approach for Applications across Multiple Domains

In this research, we introduce two new machine learning regression methods: the Ensemble Average and the Pipelined Model. These methods aim to enhance traditional regression analysis for predictive tasks and have undergone thorough evaluation across three datasets, Kaggle House Price, Boston House Price, and California Housing, using various performance metrics. The results consistently show that our models outperform existing methods in terms of accuracy and reliability across all three datasets. The Pipelined Model, in particular, is notable for its ability to combine predictions from multiple models, leading to higher accuracy and impressive scalability. This scalability allows for their application in diverse fields like technology, finance, and healthcare. Furthermore, these models can be adapted for real-time and streaming data analysis, making them valuable for applications such as fraud detection, stock market prediction, and IoT sensor data analysis. Enhancements to the models also make them suitable for big data applications, ensuring their relevance for large datasets and distributed computing environments. It is important to acknowledge some limitations of our models, including potential data biases, specific assumptions, increased complexity, and challenges related to interpretability when using them in practical scenarios. Nevertheless, these innovations advance predictive modeling, and our comprehensive evaluation underscores their potential to provide increased accuracy and reliability across a wide range of applications. The results indicate that the proposed models outperform existing models in terms of accuracy and robustness for all three datasets. The source code can be found at https://huggingface.co/DebajyotyBanik/Ensemble-Pipelined-Regression/tree/main

A data-driven implicit deep adaptive neuro-fuzzy inference system capable of manifold learning for function approximation

Fuzzy Neural Networks (FNN) have the ability of decision-making based on constructing semi-ellipsoidal clusters in the input space as the antecedent parts of their fuzzy rules. To determine the output value for each input instance, FNNs consider its membership degree to different sub-regions of the input space. However, forming such meaningful sub-regions is not possible in all applications due to the nonlinear interactions among input variables and their low information gain. Indeed, the samples could be distributed on a manifold in the input space. Therefore, to cover the input space, we need lots of rules, each representing a small region of input space. This issue decreases the generalization ability of the model along with its explainability. Consequently, to efficiently form fuzzy rules, first, it is necessary to unfold the manifold by mapping the samples to an appropriate embedding space. Next, the fuzzy rules in the form of semi-ellipsoidal regions should be constructed in this extracted feature space. Deep Fuzzy Neural Networks address this problem by representation learning through stacking multiple cascade mapping layers. In this paper, we propose a novel approach for nonlinear function approximation and time-series prediction problems, based on using the kernel trick to implicitly learn the mapping function to the new feature space. Moreover, to initialize the fuzzy rules, a KNN-based method using the kernel trick is proposed. A hierarchical Levenberg–Marquardt approach is applied to learn the model’s parameters. The performance and structure of the proposed method are studied and compared with some other relevant methods in synthetic and real-world benchmarks. Based on these experiments, the proposed method has the best performance with the most parsimonious architecture. According to these experiments, the test RMSE of the proposed method is 0.002 for Mc-Glass chaotic time-series prediction, 0.015 for a Nonlinear dynamic system identification, 0.0345 for Box–Jenkins nonlinear system identification, 0.0609 for Fuel consumption prediction of automobiles, 10.24 for Sydney stock price tracking, and 0.595 for California housing.

Impacts of Water-Related Building Moratoria on California's Housing Crisis

Impacts of Water-Related Building Moratoria on California's Housing Crisis

Modular construction's capacity to reduce embodied carbon emissions in California's housing sector

Demand for new housing construction must be balanced with minimizing embodied greenhouse gas (GHG) emissions from building materials, logistical operations, and construction activities. This study examines the potential embodied GHG benefits that an innovative housing production method, factory-built modular construction, might have in meeting the multifamily housing needs, with California as a case study. A model is developed to quantify the embodied GHG emissions from materials, transportation, and construction for representative modular housing projects, contrasting results to scenarios where housing is constructed with conventional methods. Results are scaled from single building prototypes to meeting housing demand for lower income residents in California, representing 1.1 million housing units in all 58 of the state's counties. Statewide, compared to all housing units being stick-built, most modular types achieve emission reductions of 2–22%, with potential benefits depending upon structural framing material and factory location. A parametric sensitivity analysis reveals additional key modeling variables: module size and capacity of the module delivery vehicle. A Monte Carlo analysis is conducted for each county, comparing a random allocation of modular types from all factory locations to conventionally constructed housing. Counties farthest away from module factories experience GHG emission gains, while all other counties experience emission benefits of 1–14% (removing one of the modular types increases benefits to 4–20% for all counties). While the results are California-specific, the modeling framework is applicable to any location and relevant for regions assessing the embodied carbon impacts of rapid housing construction methods.

Exponential data encoding for quantum supervised learning

Reliable quantum supervised learning of a multivariate function mapping depends on the expressivity of the corresponding quantum circuit and measurement resources. We introduce exponential-data-encoding strategies that are hardware-efficient and optimal among all nonentangling Pauli-encoded schemes, which is sufficient for a quantum circuit to express general functions having very broad Fourier frequency spectra using only exponentially few encoding gates. We show that such an encoding strategy not only reduces the quantum resources, but also exhibits practical resource advantage during training in contrast with known efficient classical strategies when polynomial-depth training circuits are also employed. When computation resources are constrained, we numerically demonstrate that even exponential-data-encoding circuits with single-layer training modules can generally express functions that lie outside the classically expressible region, thereby supporting the practical benefits of such a resource advantage. Finally, we illustrate the performance of exponential encoding in learning the potential-energy surface of the ethanol molecule and California's housing prices.

Analysis and Forecasting of California Housing

House prices have significant impact on people’s daily life, and it is essential for people to have fixed abode, to live, work and social prosperity and stability. Hence predicting House price is a meaningful and big challenge. To achieve this goal, we use California Census dataset in this project to how distinctive features (attributes) can make the house price higher or lower. The main idea of this project is to build a Regression Model that can learn from this data and make predictions of the price of a house in any block, given some useful features provided in the datasets. In the regression task, we applied cross-validation and K-Fold method on Ridege Model, Random Forest, Gradient Boosting models to select the optimal hyperparameters. Then we apply the best selected model on test set, the results show decent performance for Random Forest and Gradient Boosting. The Random Forest performs the best with MSE (Mean Squared Error) 0.290, while it takes training time 14.7 seconds. Although the Gradient Boosting takes the result of MSE is 0.295, it took a shorter training time (2.91s).

Measuring the Prospects of Newsom’s Newest Housing Laws

In fall 2022, California Governor Gavin Newsom signed two major affordable housing bills into law. This article breaks down on why affordable housing in California is a major issue right now and how these new laws will ease the housing crunch.

Meaningful Action: Evaluating Local Government Plans to Affirmatively Furthering Fair Housing in California

Meaningful Action: Evaluating Local Government Plans to Affirmatively Furthering Fair Housing in California

Impacts of Water-Related Building Moratoria on California's Housing Crisis

Impacts of Water-Related Building Moratoria on California's Housing Crisis

Analyzing Local Dynamics in House Pricing During COVID-19

Covid-19 has made it possible for people to work from home. As a result, there has been an increase in the demand for space. Since many positions now allow for the possibility of working online, people realize that having a larger space at home is necessary. This paper will use mathematical methods of data analysis and regression analysis in the context of the COVID-19 outbreak to discuss whether California house prices are suffering from an epidemic of infectious diseases.

Seismic Retrofit Added 17% to the Resale Value of Older California Houses

Seismic Retrofit Added 17% to the Resale Value of Older California Houses

California’s Transit Village Movement

Transit villages—dense, mixed-use communities near rail stops—could increase rail ridership and reduce automobile dependency; however, few good examples exist in the US. today. Barriers to building transit villages include questionable market viability, conservative lending practices, and neighborhood opposition to multi-family housing. This paper shows, however, that there is a reasonably strong market demand for well-designed transit-oriented neighborhoods. After viewing visual images of simulated transit villages, more respondents from the San Francisco Bay Area expressed a willingness to live in a moderately dense community with nice amenities than in one with a third lower densities but little neighborhood open space or consumer services. Many current occupants of transit-based housing in California are young professionals living in one or two person households with just one car. What most distinguishes tenants of transit-based housing is their tendency to work in downtowns and other locations well-served by rail transit. The demand for good quality housing near rail has allowed some rail-served apartments in the Bay Area to command rent premiums. Strong market interest in rail-based housing, coupled with recent state enabling legislation, bode favorably for the future of transit villages in California.

Building lower-carbon affordable housing: case studies from California

ABSTRACT This research explores developers’ experiences with lower-carbon multi-family affordable housing in California using three case studies that illustrate different pathways to decarbonization – improving efficiency, eliminating fossil fuel combustion for end-uses, and adopting a zero-net energy design. Qualitative analysis of in-depth interviews with stakeholders (e.g. developers, architects, consultants) involved in the development and management of three selected communities reveals several themes that influenced the design, construction and operation phases. One such theme includes uncertainty – about the future availability and cost of gas service and about operating costs and equipment performance – which was mitigated in part by adopting conservative energy modelling forecasts and elevating the role of energy consultants. Also discussed is how higher initial costs for lower-carbon designs were partially offset by higher rental income and favourable scoring for competitive financing mechanisms. Findings highlight the importance of alignment between project objectives and stakeholders’ missions and having strong advocates on the development team. Electrifying water heating, the biggest technical challenge encountered, is discussed. Overall, the case studies illustrate various technical, economic and organizational challenges associated with decarbonizing affordable housing, examples of how they were overcome, and how these experiences inform development teams’ plans to pursue lower-carbon designs in the future.

Incorporating Spatial Autocorrelation in Machine Learning Models Using Spatial Lag and Eigenvector Spatial Filtering Features

Applications of machine-learning-based approaches in the geosciences have witnessed a substantial increase over the past few years. Here we present an approach that accounts for spatial autocorrelation by introducing spatial features to the models. In particular, we explore two types of spatial features, namely spatial lag and eigenvector spatial filtering (ESF). These features are used within the widely used random forest (RF) method, and their effect is illustrated on two public datasets of varying sizes (Meuse and California housing datasets). The least absolute shrinkage and selection operator (LASSO) is used to determine the best subset of spatial features, and nested cross-validation is used for hyper-parameter tuning and performance evaluation. We utilize Moran’s I and local indicators of spatial association (LISA) to assess how spatial autocorrelation is captured at both global and local scales. Our results show that RF models combined with either spatial lag or ESF features yield lower errors (up to 33% different) and reduce the global spatial autocorrelation of the residuals (up to 95% decrease in Moran’s I) compared to the RF model with no spatial features. The local autocorrelation patterns of the residuals are weakened as well. Compared to benchmark geographically weighted regression (GWR) models, the RF models with spatial features yielded more accurate models with similar levels of global and local autocorrelation in the prediction residuals. This study reveals the effectiveness of spatial features in capturing spatial autocorrelation and provides a generic machine-learning modelling workflow for spatial prediction.

Establishing a Climate-Conscious Bill of Rights for California's Homeless

California's growing unhoused population, alongside the increasingly devastating impacts of climate change, necessitates action by California's state and local governments to protect unhoused communities from the current and anticipated impacts of climate change. Despite the public discourse surrounding both climate change and homelessness in California, policy-makers have frequently treated the two as separate and unrelated issues. failing to acknowledge how catch issue interacts with the other.This failure has allowed unhoused persons' unique vulnerability to water insecurity, heat-related illness, and the spread of disease to remain divorced from policy discussions on how California must adapt to a new and harsher climate. In addition, sea level rise and wildfires will further contribute to California's housing shortage and overall unhoused population. The collective failure of California's state and local decision-makers to address this intersectionhas led to a patchwork of laws and regulations that do not adequately confront existing or future climate burdens on unhoused persons in California. This Comment recommends that the state of California pass a climate-conscious Homeless Bill of Rights, a statutory mandate on California's municipalities to adopt specific climate adaptation strategies designed to protect unhoused persons in California. The muddled and incomplete protections contemplated by current approaches suggest that a climate-conscious Homeless Bill of Rights may provide a more complete and proactive approach to ameliorating climate burdens for unhoused Californians.

Reliability Enhancement of Inverter-Based Memristor Crossbar Neural Networks Using Mathematical Analysis of Circuit Non-Idealities

In this paper, the sensitivity of the neural network (NN) outputs to device parameter uncertainties (non-idealities) in inverter-based memristor ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IM</i> ) crossbar neuromorphic circuits is mathematically modeled and verified using exhaustive circuit and system-level simulations. The NN sensitivity is obtained by modeling the sensitivity of the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IM</i> neuron output to the non-idealities of its circuit elements. The analysis reveals a higher sensitivity of the output voltage of the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IM</i> neuron to the non-idealities of the inverters compared to the conductance variation of the memristors. Among the inverter non-idealities, horizontal shift of the inverters voltage transfer characteristic (VTC) shows the highest impact on the output voltage of the neuron. To reduce the accuracy loss due to the variations, a training approach which includes a sensitivity term in the cost function of the training phase, is suggested. The achievable improvements through the said NN training approach are evaluated. In the evaluation, the California Housing, MNIST, and Fashion MNIST datasets are employed. The results show up to 50% reduction in the NN output variations in the presence of circuit elements’ non-idealities.