1# RECORD 39f8b5119ab63b41236467364d52b44c282cb98c2# TITLE: 3# YEAR: VENUE: DOI: 4# AUTHORS: 5# PAGES: 17 CANDIDATE TABLE PAGES (1-based): [12, 13]6# ABSTRACT: 789===== PAGE 1 (score 14, numeric-paren 0, table-words 0, var-words 14) =====1011Impact of rail transit station proximity 12to commercial property prices: utilizing big data 13in urban real estate14Mohammed Ali Berawi1*, Perdana Miraj2,3 , Gunawan Saroji3 and Mustika Sari315Introduction16Investment in rail transit does not only offer benefits to the public interest, such as 17increasing physical activity [1], releasing traffic congestion [2, 3], reducing emission [4], 18and expanding consumer amenities [5], but it also enables property owners nearby tran-19sit stations to capitalize their assets for greater benefits due to the land value uplift as 20the effect of accessibility improvement. The increases in land value indicate the posi-21tive impact of rail transit to the local economy, people’s quality of life, and the overall 22property market. The capitalization of real estate market is a combination of structural 23characteristics, surrounding environment, physical attributes, and accessibility which 24created the market price of an area [6, 7].25Abstract 26Urban transport investments have contributed to the exponential increase of value 27from land and properties around the built infrastructure. Although literature had 28shown evidence of value uplift from the residential property due to transit develop-29ment, little is known about the impact on commercial property values. This paper aims 30to evaluate the impact of rail transit proximity to the commercial property market by 31taking into account the pre-operation of the LRT project in Jakarta, Indonesia. This 32study utilizes a big data approach to accelerate research data processing by employing 33data mining method, as well as geographical information system (GIS) and hedonic 34price modeling (HPM) to investigate the property prices to formulate empirical 35evidence for the research. The results show opposite evidence compared to previous 36studies which argued that accessibility may contribute to the property price when 37closer to the transit station. The findings indicate that proximity to rail transit has an 38insignificant impact on the commercial property price compared to other variables 39such as building size, number of rooms, location, and hospitals. A comparison of the 40findings between this research with other studies was discussed and recommendation 41for further research development was proposed.42Keywords: Commercial property, Hedonic price model, Jakarta indonesia, Proximity 43premium, Rail transit, Value capture44Open Access45© The Author(s) 2020. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, 46adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and 47the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material 48in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material 49is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the 50permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativeco51mmons.org/licenses/by/4.0/.52RESEARCH53Berawi et al. J Big Data (2020) 7:71 54https://doi.org/10.1186/s40537-020-00348-z55*Correspondence: 56maberawi@eng.ui.ac.id 571 Department of Civil 58Engineering, Universitas 59Indonesia, Depok 16424, 60Indonesia61Full list of author information 62is available at the end of the 63article646566===== PAGE 12 (score 30, numeric-paren 6, table-words 8, var-words 5) =====6768Page 12 of 1769Berawi et al. J Big Data (2020) 7:71 70the two variables and a value close to 0 indicates a weak relationship. On the other hand, 71positive ( +) and negative (-) signs suggest the direction of the relationship between the 72two variables. If the value is + (positive), then the two variables have a direct relation-73ship. The significance of the variable can be seen from Sig. (2-tailed) when the value 74lower than 0.05.75Among three variables (distance, number of rooms, and building size), as shown in 76Table 5, the variable of building size shows a correlation coefficient close to 1 and sig. 77A 2-tailed value lower than 0.05. A positive mark means that a larger building size con-78tributes to a higher property price. In terms of location, three of the stations, namely 79Rasuna Said, Dukuh Atas, and Cawang, are highly correlated and contribute to the prop-80erty price, respectively. Subsequently, the result suggests excluding CBD and university 81as both of them do not significantly contribute to the property price.82The HPM equation uses SPSS software by taking into account the stepwise regres-83sion method. This method evaluated the input and produced four equation models as 84the best alternative in the case study. The best equation selected based on the high-85est R-squared close to 1. It will represent the impact of independent variables on the 86dependent variable. Based on the result in Table 6, model 4 is the best model due to the 87highest R-squared with 0.919 and suggests a lower error value with 7.80%, among other 88variables.89Following the correlation test, another round of tests is performed, including multi-90collinearity and heteroscedasticity tests. The multi-collinearity test aims to determine 91inter-correlation between independent variables in a regression model. The model will 92proceed for further analysis when any correlation between independent variables was 93not found. This test was taking into account tolerance and VIF score, which should be 94higher than 0.10 and less than 10, respectively. The result shows that all four models 95(Table 6) do not correlate with independent variables. However, the fourth model which 96Table 5 Correlation test between dependent and independent variables 97* Correlation is significant at the 0.05 level (2-tailed)98** Correlation is significant at the 0.01 level (2-tailed)99Ln Price100Sig. (2-tailed)101N102Ln Distance103− 0.0911040.38010595106Ln NRooms107− 0.0461080.65910995110Ln BSize1110.951**1120.00011395114Karet Kuningan1150.0261160.80511795118Dukuh Atas1190.212*1200.03912195122Rasuna Said123− 0.216*1240.03512595126Cawang127− 0.202*1280.04912995130Kuningan1310.1351320.19113395134Cikoko135− 0.0081360.93613795138Ciliwung1390.1131400.27614195142Schools143− 0.212*1440.03914595146University147− 0.0441480.67514995150Hospital1510.212*1520.03915395154CBD1550.0481560.64615795158159160===== PAGE 13 (score 22, numeric-paren 0, table-words 3, var-words 7) =====161162Page 13 of 17163Berawi et al. J Big Data (2020) 7:71 164 165includes four variables (Building Size, Hospital, Rasuna Said, and Number of Rooms) 166shows the highest score among others.167Based on the findings, the formula regarding the effect of proximity to transit station 168on property values in the case study is presented as follows.169where,170Ln Price = Log Natural of property price (US$).171Ln BSize = Log Natural building size (square meter).172Ln NRooms = Log Natural number of rooms (unit).173Hospital = Location of hospital within 1 km (dummy).174RasunaSaid = Property location within 1 km from Rasuna Said (dummy).175Overall, two variables that consist of building size and the number of rooms signifi-176cantly contribute to the property price around the transit station. A larger building is suit-177able for commercials and offices, which requires large space to perform daily activities. 178The findings showed that expanding the building size every square meter will increase 179the property price by US$ 6.45. These findings also found two variables consist of hospi-180tal and Rasuna Said—a location of transit station generates negative signs, thus create an 181opposite correlation. Hospital existence in a 1 km radius of transit station is believed to 182decrease property price about 6.8% or equal to US$ 7.29 while the property located 1 km 183from Rasuna Said station is cheaper US$ 8.21 than properties beyond the radius.184Discussion185Previous studies showed insightful evidence to create a basis comparison for the pre-186sent studies. Despite all these findings, the property market on each country has differ-187ent characteristics and conditions, causing direct comparisons rather difficult. Table 1 188(2)189LnPrice = 14.288 + 0.524 Ln_BSize −0.068 Hospital190−0.077 RasunaSaid + 0.032 Ln_NRooms + %error191Table 6 Result of multi-collinearity and heteroscedasticity tests192Model193Unstandardized 194coefficients195Standardized 196coefficients197t198Sig199Collinearity 200statistics201R-squared202B203Std. error204Beta205Tolerance206VIF2071208(Constant)20914.1852100.119211119.2832120.0002130.904214Ln BSize2150.5312160.0182170.95121829.8232190.0002201.0002211.0002222223(Constant)22414.2952250.120226119.0172270.0002280.912229Ln BSize2300.5242310.0172320.94023330.4082340.0002350.9842361.017237Hospital238− 0.0852390.029240− 0.092241− 2.9652420.0042430.9842441.0172453246(Constant)24714.3242480.118249121.5572500.0002510.916252Ln BSize2530.5202540.0172550.93225630.7372570.0002580.9732591.028260Hospital261− 0.0692620.029263− 0.074264− 2.3942650.0192660.9292671.077268RasunaSaid269− 0.0742700.031271− 0.074272− 2.3702730.0202740.9282751.0782764277(Constant)27814.2882790.117280122.2732810.0002820.919283Ln BSize2840.5242850.0172860.93928731.3642880.0002890.9622901.040291Hospital292− 0.0682930.028294− 0.073295− 2.4032960.0182970.9292981.077299RasunaSaid300− 0.0773010.031302− 0.077303− 2.5103040.0143050.9263061.080307Ln NRooms3080.0323090.0153100.0623112.1113120.0383130.9863141.014315316317===== PAGE 14 (score 18, numeric-paren 0, table-words 0, var-words 18) =====318319Page 14 of 17320Berawi et al. J Big Data (2020) 7:71 321illustrates selected studies regarding the impact of rail station on commercial proper-322ties worldwide. Unlike previous studies that showed premium accessibility to rail transit, 323this research found the accessibility attribute to the transit station has an insignificant 324impact on the property price. In contrast, structural and neighborhood attributes play a 325critical role in increasing the price of property nearby rail transit.326There are some reasons the variable of distance to transit was out of the equation. 327First, data mining was conducted starting from September 2018 to March 2019, where 328the transit stations are yet to operate. At this stage, owners believed transit stations offer 329less added-value when the users still require additional modes of transportation (bus or 330motorbike ride-hailing) to reach their property. Accessibility within walking distance is 331argued to remain unattractive due to various reasons. Citizens of Jakarta tend to have a 332negative experience when accessing destinations through pedestrian paths since those 333paths are still lacking in width outside the arterial roads; usually only 1 m wide, lack-334ing in amenities, and lacking in the number of lightings. Moreover, poor condition of 335walkway pavements, street vendors occupying the sidewalks, and the excessive exposure 336from vehicle noise and pollution are also among other reasons. Therefore, it is under-337standable from the viewpoint of property owners to not taking into account better acces-338sibility and mobility as they believe that do not significantly correlate to property prices.339Second, location with strong branding plays a significant role in determining prop-340erty prices despite the far location from the rail transit station. Rasuna Said, which was 341included in the formula, is located in the Kuningan area of South Jakarta that provides 342a balanced lifestyle between working and leisure. This area comprises a variety of office 343buildings, hotels, embassy offices, and a variety of tourist attractions, including shop-344ping malls, art galleries, public open space, and many others that can be regarded as a 345place to relax or refresh after a day of work. However, Rasuna Said station in this project 346is argued to be located in a bad environment where there is a slum area nearby, bad 347odor from the polluted river, and it is crime-prone due to the incomplete street ameni-348ties. Therefore, it is not a surprise when the property in Rasuna Said has a higher price 349though it is outside of 1 km walkability radius compared to those located with proximity 350from the rail station.351Conclusion352There is a huge potential to utilize a value capture approach to finance rail transit pro-353jects by fully understanding the positive impact of accessibility improvement due to the 354existence of transit stations on property values. Although capitalization of property mar-355ket around transit stations has been extensively investigated in developed countries such 356as in European Countries, the United States, and the East Asian region, research in the 357same topics in developing countries such as Indonesia remains limited. This research 358elaborates properties listed in several real estate marketplaces and takes into account 359seven LRT stations located in Jakarta, Indonesia, that are planned to fully operate in 3602021 to fill the research gaps.361Most studies use geographical information system (GIS) and hedonic price mod-362eling (HPM) by taking into account the contractual price of property market. For 363instance, Barbara et al. [13] elaborated property sales data in Australia and New Zea-364land from a property business company. On the other hand, Mohammad et al. [17] 365