Housing Price Forecasting in California: A Machine Learning Approach for 2021 - Essay Sample

Project Goals and Background

Housing is part of the basic needs of life. In any state or region, people need houses or a roof where to rest after work. As a basic need, it is vital for regulators and to ensure that houses are affordable. However, it is not always the case. In California, homes are quite expensive, and it has been the case for the last decade. Since the financial crisis of 2008, Prices have escalated. This project seeks to review the housing situation in California. The main goal is to develop a high accuracy model that can help predict home prices in 2021. A prediction must include all the necessary parameters, which shall help potential homeowners plan their home purchase plans in California.

Is your time best spent reading someone else’s essay? Get a 100% original essay FROM A CERTIFIED WRITER!

Order now

Analysis of Requirements

In order to deliver the best model, the project must be undertaken using price forecasting technologies available in the market. The machine learning approach is the most appropriate for this case. It could ensure that the best model is developed from the process. One shall also require descriptive and predictive analytics in the model. Computer knowledge, the hardware infrastructure, and software needed to model the deliverable and make the final product.

Project Deliverables

The project shall deliver a report on the housing situation in California. Accompanying the report shall be predictors of the cost of housing in the state and the role they play in determining the value of homes. The most crucial deliverable in this project is a computer-based model to predict house prices in 2021. The most essential quality of the model is accuracy and precision.

Technology and Solution Survey

There is a litany of technologies for different purposes in the world today. Therefore, one could be at a loss in selecting an appropriate approach in this machine learning process, but there are existing platforms for users. Dynac CPM, Solver, IBM Planning Analytics, Plan Guru, Anaplan, and Vena are some of the software solutions that could be applied in this case. The selection shall depend on availability, cost, effectiveness, and ability to deliver the required results. Some of the software is available in open-source web, whereas others require a subscription to access and use.

Literature Survey of Existing Research

Price and cost forecasting is an essential concept in anything that involves buying and selling. Homeowners sometimes find themselves at a loss when trying to plan future purchases because they are unsure how prices will behave. Ardila et al. (2017) said that for that reason, most people find themselves inadequately prepared when the time to purchase a house comes. However, they could have been better prepared had there been a way to predict the cost they will pay in the future when tome to purchase comes. According to Bazan-Krzywoszanska and Bereta (2018), forecasting is a fundamental process that should not be ignored by players in the real estate sector. Bazan-Krzywoszanska and Bereta (2018) recommend machine learning regression models, as they ascertain accuracy and precision in their functionalism. They allow the predictor to incorporate as many parameters and indicators as possible, making it possible to deliver an accurate prediction of the cost. Therefore, this project shall aim to meet the recommendations by the authors that accurate and precise models should be developed to assist home buyers. The model should be easy to use and apply for all.

References

Ardila, D., Sanadgol, D., Cauwels, P., & Sornette, D. (2016). Identification and critical time forecasting of real estate bubbles in the USA. Quantitative Finance, 17(4), 613-631. https://doi.org/10.1080/14697688.2016.1207796

Bazan-Krzywoszanska, A., & Bereta, M. (2018). The use of urban indicators in forecasting a real estate value using the deep neural network. Reports on Geodesy and Geoinformatics, 106(1), 25-34. https://doi.org/10.2478/rgg-2018-0011