Article Preview
Top1. Introduction
Data mining provides information from data sets that could be utilized by drawing comparisons, associating patterns, classifying objects, to predicting future trends, based on the current and past standards of any given situation provided a clear set of data. Realizing the importance and the scope of mining for information, this article provides focus and predicts the market values of properties situated in major urban locations on mainland Fiji that are being advertised on the social media platform, Facebook, based on the current and the past sale of properties within these respective areas. The introduction and progression towards Web2.0 have transformed the use of internet, enabling buyers with the ability to comment, review, blog, update status amidst many other forms of interaction and active participation. One of the new revelations (Branko et al., 2013) of such usage and participation has been the introduction of big data, with diverse, unstructured stream of information floating on the web containing blends of data such as demographics, lifestyle choices, opinions, as well as mentions of properties and items in possession by the people, among many others. The authors choose Facebook as the social media platform to scrape data from, as it is the most common social media platform of choice in Fiji, and also since Facebook provides user groups based on common interests (in our case, property sales groups created to advertise properties).
Too often in real estate, (Geojournal, 2020) the process of valuation can come across as a high-brow exercise of thumb-sucking. The realtor will come over, kick the proverbial tires, and then produce an estimated value with very little “quantitative” insight. Perhaps the process is exacerbated by the emotional attachment that owning property brings given that for many, a house will be the largest financial investment made in a lifetime. The comparable property valuation approach is most common model for determining residential real estate and recent sales of similar or properties to determine the valuation of a subject property. The sales price are adjusted based on differences between these and the subject property. For example, if a comparable property has an additional bathroom, then the estimated value of the bathroom is subtracted from its observed sales price. Real estate is considered to be more heterogeneous, so the comparable valuation approach is used less frequently (Doumpos et al. 2020). The income approach, based on the concept that the intrinsic value of an asset is equivalent to the sum of all its discounted cash flows, is more commonly applied across two methods. The first is similar to the present value of an annuity, the direct capitalization method uses the net operating income (NOI) of a property divided by the “cap rate” to establish a value. The cap rate contains an implied discount rate and future growth rate of net operating income. While the second method involves discounted cash flow method provides the present value of future cash flows over a set period of time, with a terminal value that is estimated from using a terminal cap rate. The final technique is the cost approach, which estimates value based on the cost of acquiring an identical piece of land and building a replica of the subject property as presented by José-Luis et al. (2020). Then cost of the project is depreciated based on the current state of obsolescence of the subject property. Similar to the adjustments in the comparable sales approach, the goal is to closely match the subject property. The cost approach is less frequently used than the other two approaches.
The aim of the to identify texts from structured as well as unstructured posts from social media, which infer to properties such as lands and houses attached with variables such as price, along with mentions of other details and attributes. The research intends to further the work and evaluate by annotating these texts and analyzing the identification, and storing these identifications with its variable in an updated dataset. Use of data mining techniques such as linear regression, and random forest model is performed to determine the predicted valuation figure and testing it with the current valuation reports on the selected properties which can be used to compare against prices advertised on the social media groups.