kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Construction of house price indices in Dar es Salaam: Suggestion of a practical model for Tanzania amid data constraints
KTH, School of Architecture and the Built Environment (ABE), Real Estate and Construction Management. Ardhi University (ARU), Dar Es Salaam, Tanzania.ORCID iD: 0000-0002-3602-2071
2025 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Real estate significantly influences economic growth, with prices shaped by utility attributes and buyer willingness, making price dynamics crucial for stakeholders. In nascent real estate markets like Dar es Salaam, where data is less integrated and transactions often involve informal agents, creating accurate price indices is challenging, and methodologies may need to incorporate both formal and informal data sources, potentially with the help of machine learning techniques to improve predictions. Nevertheless, the Dar es Salaam housing market lacks indices, despite the existence of data sources, particularly formal and informal real estate agents. The main objective of this doctoral thesis is to examine the adoption of the best method for developing a house price index (HPI) for Dar es Salaam, Tanzania's most active real estate submarket, which shares operational characteristics with other regional submarkets in the country.

This thesis consists of four papers, utilising a survey strategy and cross-sectional data from real estate agents. It examines the feasibility of using informal real estate agents' data to establish a house price index in Dar es Salaam, the impact of spatial dependence on the index, the impact of informal and formal agents' data sources on the index and the use of machine learning techniques for property valuation, aiming to highlight its feasibility for house pricing.

The findings of the study indicate that the hedonic approach, with the informal agents’ data, appears to yield a useful house price index that shows a steady but rising trend (paper I). The hedonic pricing model for Dar es Salaam may not require spatial considerations due to data limitations, suggesting that proximity factors and spatial dependence may not significantly improve the house price index (paper II). Since the resulting price trend seems to be consistent with both formal and informal real estate agents, the house price index can be constructed using data from both sources. Nevertheless, incorporating data from various agent categories improves the index, likely due to the larger sample size (paper III). Despite challenges with informal market data, machine learning techniques can effectively estimate housing worth, with some methods consistently outperforming others (paper IV).

The study poses several implications for various stakeholders. The hedonic modelling approach is effective for developing house price indices in Dar es Salaam's nascent housing market. Policies must encourage informal agents to share their property transaction data. This could be through mandating the digitisation of informal transactions. Policies should also encourage standardised data formats and reporting for both formal and informal housing transactions to ensure consistency and reliability in integrating datasets into machine learning models. Data privacy regulations must ensure secure and ethical handling of sensitive information from individuals and informal agents. 

Abstract [sv]

Fastigheter påverkar avsevärt ekonomisk tillväxt, med priser som formas av nyttoegenskaper och köparens vilja, vilket gör prisdynamiken avgörande för intressenter. På begynnande fastighetsmarknader som Dar es Salaam, där data är mindre integrerade och transaktioner ofta involverar informella agenter, är det en utmaning att skapa korrekta prisindex, och metoder kan behöva införliva både formella och informella datakällor, eventuellt med hjälp av maskininlärningstekniker för att förbättra förutsägelser. Ändå saknar bostadsmarknaden i Dar es Salaam index, trots att det finns datakällor, särskilt formella och informella fastighetsmäklare. Huvudsyftet med denna doktorsavhandling är att undersöka antagandet av den bästa metoden för att utveckla ett husprisindex (HPI) för Dar es Salaam, Tanzanias mest aktiva fastighetsdelmarknad, som delar operativa egenskaper med andra regionala delmarknader i landet.

Detta examensarbete består av fyra artiklar, som använder en undersökningsstrategi och tvärsnittsdata från fastighetsmäklare. Den undersöker genomförbarheten av att använda informella fastighetsmäklares data för att upprätta ett husprisindex i Dar es Salaam, effekten av rumsligt beroende av indexet, effekten av informella och formella agenters datakällor på indexet och användningen av maskininlärningstekniker för fastighetsvärdering, i syfte att belysa dess genomförbarhet för husprissättning.

Resultaten av studien indikerar att det hedoniska tillvägagångssättet, med de informella agenternas data, verkar ge ett användbart husprisindex som visar en stadig men stigande trend (artikel I). Den hedoniska prissättningsmodellen för Dar es Salaam kanske inte kräver rumsliga överväganden på grund av databegränsningar, vilket tyder på att närhetsfaktorer och rumsligt beroende kanske inte avsevärt förbättrar husprisindex (artikel II). Eftersom den resulterande prisutvecklingen verkar överensstämma med både formella och informella fastighetsmäklare, kan husprisindex konstrueras med hjälp av data från båda källorna. Ändå förbättras indexet genom att införliva data från olika agentkategorier, troligen på grund av den större urvalsstorleken (artikel III). Trots utmaningar med informell marknadsdata kan maskininlärningstekniker effektivt uppskatta bostadsvärde, med vissa metoder som konsekvent överträffar andra (artikel IV).

Studien har flera konsekvenser för olika intressenter. Den hedoniska modelleringsmetoden är effektiv för att utveckla husprisindex på Dar es Salaams begynnande bostadsmarknad. Policyer måste uppmuntra informella agenter att dela sina fastighetstransaktionsdata. Detta kan vara genom att kräva digitalisering av informella transaktioner. Policyer bör också uppmuntra standardiserade dataformat och rapportering för både formella och informella bostadstransaktioner för att säkerställa konsekvens och tillförlitlighet vid integrering av datauppsättningar i maskininlärningsmodeller. Datasekretessbestämmelser måste säkerställa säker och etisk hantering av känslig information från individer och informella agenter. 

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2025. , p. 40
Series
TRITA-ABE-DLT ; 2513
Keywords [en]
Nascent housing markets, Informal and formal real estate agents, House price index, Spatial dependence, Machine learning
Keywords [sv]
Nya bostadsmarknader, Informella och formella fastighetsmäklare, Husprisindex, Spatial dependence, Machine learning
National Category
Business Administration
Research subject
Real Estate and Construction Management
Identifiers
URN: urn:nbn:se:kth:diva-363131ISBN: 978-91-8106-300-4 (print)OAI: oai:DiVA.org:kth-363131DiVA, id: diva2:1956407
Public defence
2025-05-26, At 11:00 am Tanzania time: DMTC Building, Ardhi University, Dar es Salaam, Tanzania, At 10 am Swedish time: public video conference link https://us02web.zoom.us/j/83183762796?pwd=dAoGl3cnyIg1f9plRHYj1Pcb3jiTwn.1, Dar es Salaam, 10:00 (English)
Opponent
Supervisors
Funder
Sida - Swedish International Development Cooperation Agency
Note

QC 20250507

Available from: 2025-05-07 Created: 2025-05-06 Last updated: 2025-05-15Bibliographically approved
List of papers
1. Developing house price indices in nascent markets: the case of Dar es Salaam, Tanzania
Open this publication in new window or tab >>Developing house price indices in nascent markets: the case of Dar es Salaam, Tanzania
2025 (English)Manuscript (preprint) (Other academic)
Abstract [en]

Purpose Despite the presence of different data sources and the need for a house price index, there is no house price index for Dar es Salaam. Previous studies have not explored the congruence of various data sources for any house price index method. The study determines the feasibility of utilising data from informal real estate agents to establish a meaningful house price index for the nascent Dar es Salaam market.

Design/methodology/approach Given the survey data collected in person from the informal real estate agents, the paper explores the different methods for creating an index and ultimately uses the hedonic method to test the meaningfulness of the resulting index. The basis of the index is pooled cross-sectional data for 500 property transactions from 2010 to 2019.

Findings Data from the informal agents could be useful for creating the hedonic house price index for Dar es Salaam, as the resulting index appears to be reasonably meaningful. Despite the limitations of the data, such as poor record-keeping and the hurdles in collecting the non-centralised data from the agents, the resulting hedonic model could explain about 75% of property price variation. Among the other factors, house prices in Dar es Salaam are highly linked to location.

Originality/Value The article brings new knowledge that it is possible to use informal agents' data as a starting point for the Dar es Salaam house price index.

Keywords
House price index, Data availability, Nascent housing markets, Informal real estate agents
National Category
Business Administration
Research subject
Real Estate and Construction Management
Identifiers
urn:nbn:se:kth:diva-363165 (URN)
Note

Manuscript being revised after comments from the Property Management Journal

QC 20250506

Available from: 2025-05-06 Created: 2025-05-06 Last updated: 2025-05-13Bibliographically approved
2. The effect of proximity and spatial dependence on the house price index for Dar es Salaam
Open this publication in new window or tab >>The effect of proximity and spatial dependence on the house price index for Dar es Salaam
2024 (English)In: International Journal of Housing Markets and Analysis, ISSN 1753-8270, E-ISSN 1753-8289, Vol. 17, no 4, p. 945-963Article in journal (Refereed) Published
Abstract [en]

Purpose: This study aims to examine the effect of proximity and spatial dependence on the house price index for the nascent market Dar es Salaam, Tanzania. Despite the ongoing housing market transactions, there is no single house price index that takes into account proximity and spatial dependence. The proximity considerations in question are proximal to arterial roads, public hospitals, an airport and food markets. Previous studies on sub-Saharan Africa have focused on the ordinary least squares (OLS)-based hedonic model for the index and ignored spatial and proximity considerations. Design/methodology/approach: Using the OLS and spatial econometric approach, the paper tests for the significance of the two effects – proximity and spatial dependence in the hedonic price model with year dummy variables from 2010 to 2019. The paper then compares the three indices in the following configurations: without the two effects, with proximity factors only, and with both effects, i.e. proximity and spatial dependence. Findings: The inclusion of proximity factors and spatial dependence – spatial autocorrelation – seems to improve the hedonic price model but does not significantly improve the house price index. However, further research should be called for on account of the nascent nature of the market. Originality/value: The paper brings new knowledge by demonstrating that it may not be necessary to take into account proximity factors and spatial dependence for the Dar es Salaam house price index.

Place, publisher, year, edition, pages
Emerald, 2024
Keywords
House price index, Proximity, Spatial autocorrelation, Spatial dependence
National Category
Economics
Identifiers
urn:nbn:se:kth:diva-350058 (URN)10.1108/IJHMA-09-2022-0136 (DOI)000939936500001 ()2-s2.0-85149304675 (Scopus ID)
Note

QC 20240706

Available from: 2024-07-06 Created: 2024-07-06 Last updated: 2025-05-13Bibliographically approved
3. Hedonic house price index for Dar es Salaam: examining the effects of data from informal and formal real estate agents
Open this publication in new window or tab >>Hedonic house price index for Dar es Salaam: examining the effects of data from informal and formal real estate agents
2024 (English)In: Journal of Building and Land Development, ISSN 0856-0501, Vol. 25, no 2, p. 56-70Article in journal (Refereed) Published
Abstract [en]

The Dar es Salaam housing market is among the nascent one in Sub-Saharan Africa with limited availability of housing transaction data. This has contributed to the absence of house price indices to reveal the house price dynamics. However, there are both formal and informal real estate agents with housing transaction data which could be useful in constructing a house price index. Nevertheless, no studies have examined the potential of data from both informal and formal real estate agents for developing house price indices. Using a pooled cross-sectional sample of data from both informal and formal agents, this study determines the effect of the two data sources on the house price index for Dar es Salaam city. The study employs OLS-based hedonic pricing and the spatial hedonic models (Spatial Durbin). Results from this study indicate that, adding data from formal real estate agents to the data from informal agents seems to marginally improve the hedonic model and produce a smoother house price index. However, the marginal improvement is probably due to the differences in the volumes of data rather than the data source. Findings suggest that, a house price index for Dar es Salaam could be developed using a combination of data from both formal and informal real estate agents.

Place, publisher, year, edition, pages
Dar es Salaam: ARDHI University, 2024
Keywords
Property transactions, housing market, OLS, spatial hedonic models
National Category
Economics Economics and Business
Identifiers
urn:nbn:se:kth:diva-363076 (URN)
Note

QC 20250506

Available from: 2025-05-05 Created: 2025-05-05 Last updated: 2025-05-13Bibliographically approved
4. Machine Learning Valuation in Dual Market Dynamics: A Case Study of the Formal and Informal Real Estate Market in Dar es Salaam
Open this publication in new window or tab >>Machine Learning Valuation in Dual Market Dynamics: A Case Study of the Formal and Informal Real Estate Market in Dar es Salaam
2024 (English)In: Buildings, E-ISSN 2075-5309, Vol. 14, no 10, article id 3172Article in journal (Refereed) Published
Abstract [en]

The housing market in Dar es Salaam, Tanzania, is expanding and with it a need for increased market transparency to guide investors and other stakeholders. The objective of this paper is to evaluate machine learning (ML) methods to appraise real estate in formal and informal housing markets in this nascent market sector. Various advanced ML models are applied with the aim of improving property value estimates in a market with limited access to information. The dataset used included detailed property characteristics and transaction data from both market types. Regression, decision trees, neural networks, and ensemble methods were employed to refine property appraisals across these settings. The findings indicate significant differences between formal and informal market valuations, demonstrating ML’s effectiveness in handling limited data and complex market dynamics. These results emphasise the potential of ML techniques in emerging markets where traditional valuation methods often fail due to the scarcity of transaction data.

Place, publisher, year, edition, pages
MDPI AG, 2024
Keywords
Dar es Salaam, machine learning, real estate valuation, the formal and informal housing market, thin market
National Category
Economics and Business
Identifiers
urn:nbn:se:kth:diva-355968 (URN)10.3390/buildings14103172 (DOI)001342626300001 ()2-s2.0-85207345001 (Scopus ID)
Note

QC 20241111

Available from: 2024-11-06 Created: 2024-11-06 Last updated: 2025-05-13Bibliographically approved

Open Access in DiVA

summary(724 kB)17 downloads
File information
File name FULLTEXT01.pdfFile size 724 kBChecksum SHA-512
664d620f57db287b6f4402368f93c03db23227d950a23ca437da993d6c96253623afc814208f5e8bc9f8fd78551063674a9fe26765eef11906ba7611cccb9784
Type summaryMimetype application/pdf
errata(95 kB)10 downloads
File information
File name ERRATA01.pdfFile size 95 kBChecksum SHA-512
e322209580531c55d5f0df65e139b31daa5db762fafdf841a17019df38c38405b4d640971172d52abb0a8fedf22784e31b53d89bf91b27d1910a4fd5f089218c
Type errataMimetype application/pdf

Authority records

Nyanda, Frank

Search in DiVA

By author/editor
Nyanda, Frank
By organisation
Real Estate and Construction Management
Business Administration

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1007 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf