IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2608.01544.html

Measuring Product Quality Using Images: The CLIP Q-Score and an Application to Real Estate

Author

Listed:
  • Fabian Slonimczyk
  • Danila Karapsin

Abstract

The CLIP Q-score is a novel, safe, fully reproducible, and computationally efficient method for extracting objective product quality metrics from visual data using contrastive language-image pre-training. We introduce the technique and provide an extensive application to real estate data from an online platform ($\sim500,000$ images). Our open-source metric aligns with LLM assessments and proves to be a powerful predictor of housing market prices for both sales and rentals. We also show that a higher CLIP Q-store is associated with better liquidity (reduced time on the market), especially for properties on sale.

Suggested Citation

  • Fabian Slonimczyk & Danila Karapsin, 2026. "Measuring Product Quality Using Images: The CLIP Q-Score and an Application to Real Estate," Papers 2608.01544, arXiv.org.
    • Handle: RePEc:arx:papers:2608.01544
    as

    Download full text from publisher

    File URL: https://arxiv.org/pdf/2608.01544
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Obaid, Khaled & Pukthuanthong, Kuntara, 2022. "A picture is worth a thousand words: Measuring investor sentiment by combining machine learning and photos from news," Journal of Financial Economics, Elsevier, vol. 144(1), pages 273-297.
    2. Gorin, Clement & Heblich, Stephan & Zylberberg, Yanos, 2025. "State of the Art: Economic Development Through the Lens of Paintings," CEPR Discussion Papers 20416, Centre for Economic Policy Research.
    3. Daria Dzyabura & Siham El Kihal & John R. Hauser & Marat Ibragimov, 2023. "Leveraging the Power of Images in Managing Product Return Rates," Marketing Science, INFORMS, vol. 42(6), pages 1125-1142, November.
    4. Adam Nowak & Patrick Smith, 2017. "Textual Analysis in Real Estate," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 32(4), pages 896-918, June.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Ardyn Nordstrom & Morgan Nordstrom & Vamuyan Sesay & Matthew D. Webb, 2026. "Representation Risk in Pretrained Image Encoders," Papers 2609.35470, arXiv.org.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Li, Mingfang & Choudhury, Askar H. & Du, Jiangang, 2026. "Impact of impulse buying on product return in online shopping," Journal of Retailing and Consumer Services, Elsevier, vol. 89(PA).
    2. Diego Pitta Jesus & Elvira Helena Oliveira Medeiros & Lucas Lúcio Godeiro & Andressa Lemes Proque, 2025. "Forecasting Brazilian Stock Market Using Sentiment Indices from Textual Data, Chat-GPT-Based and Technical Indicators," Computational Economics, Springer;Society for Computational Economics, vol. 66(5), pages 3735-3780, November.
    3. Liang, Chao & Xu, Yongan & Wang, Jianqiong & Yang, Mo, 2022. "Whether dimensionality reduction techniques can improve the ability of sentiment proxies to predict stock market returns," International Review of Financial Analysis, Elsevier, vol. 82(C).
    4. Ming Gu & David Hirshleifer & Siew Hong Teoh & Shijia Wu, 2025. "GIFfluence: A Visual Approach to Investor Sentiment and the Stock Market," Papers 2512.20027, arXiv.org.
    5. Xia, Hui & Zhang, Longyun & Chen, Junjie & Wang, Xinchun, 2025. "Decoding virtual influencer endorsement using machine learning: The role of virtual influencer, posting, and disclosure characteristics," Journal of Retailing and Consumer Services, Elsevier, vol. 87(C).
    6. Gang Kou & Yang Lu, 2025. "FinTech: a literature review of emerging financial technologies and applications," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 11(1), pages 1-34, December.
    7. Haowen Tian & Wenlan Tony Xie & Yanlei Zhang, 2026. "Reading Between the Reels: An AI‐Driven Approach to Analysing Movie Review Sentiment and Market Returns," International Journal of Finance & Economics, John Wiley & Sons, Ltd., vol. 31(3), pages 3948-3980, July.
    8. Lin Ren & Yingyue Sun & Deping Xiong & Yu Wei, 2025. "Evaluating the Impact of Private and Public Sentiments on the Linkage Between Gold and Stock Markets: Evidence from China," Evaluation Review, , vol. 49(4), pages 739-772, August.
    9. Albrecht, Disen Huang & Anantharaman, Divya & Zhao, Keyi, 2025. "Is a picture worth a thousand words? Image usage in ESG reports," Accounting, Organizations and Society, Elsevier, vol. 115(C).
    10. Wagner, Moritz & Wei, Xiaopeng, 2024. "Ambiguous investor sentiment," Finance Research Letters, Elsevier, vol. 67(PA).
    11. Kimberly F. Luchtenberg & Michael J. Seiler & Hua Sun, 2019. "Listing Agent Signals: Does a Picture Paint a Thousand Words?," The Journal of Real Estate Finance and Economics, Springer, vol. 59(4), pages 617-648, November.
    12. Yan Cheng & Jingbo Wang & Xinyu Cao & Zuo-Jun Max Shen & Yuhui Zhang, 2026. "A Deep-DiD Method to Estimate Heterogeneous Treatment Effects: Application to Content Creator Selection," Marketing Science, INFORMS, vol. 45(2), pages 258-279, March.
    13. Tianxiang Hao & Qingfu Liu & Deyu Miao & Yiuman Tse, 2025. "Predicting Commodity Returns Through Image‐Based Price Patterns," Journal of Futures Markets, John Wiley & Sons, Ltd., vol. 45(12), pages 2434-2456, December.
    14. Hartmann, Jochen & Exner, Yannick & Domdey, Samuel, 2025. "The power of generative marketing: Can generative AI create superhuman visual marketing content?," International Journal of Research in Marketing, Elsevier, vol. 42(1), pages 13-31.
    15. Alex Burnap & John R. Hauser & Artem Timoshenko, 2019. "Product Aesthetic Design: A Machine Learning Augmentation," Papers 1907.07786, arXiv.org, revised Nov 2022.
    16. Daria Dzyabura & Renana Peres & Irina Linevich, 2025. "Color Analytics for Data-Driven Brand Communications," Working Papers w0292, New Economic School (NES).
    17. Julie Bourbeillon & Thomas Coisnon & Damien Rousselière & Julien Salanié, 2021. "Characterising the Landscape in the Analysis of Urbanisation Factors: Methodology and Illustration for the Urban Area of Angers," Economie et Statistique / Economics and Statistics, Institut National de la Statistique et des Etudes Economiques (INSEE), issue 528-529, pages 109-128.
    18. Anuj Kapoor & Madhav Kumar, 2025. "Frontiers: Generative AI and Personalized Video Advertisements," Marketing Science, INFORMS, vol. 44(4), pages 733-747, July.
    19. Gao, Xiang & Koedijk, Kees & Walther, Thomas & Wang, Zhan, 2025. "Relative investor sentiment," International Review of Economics & Finance, Elsevier, vol. 100(C).
    20. Tran, Vu Le, 2023. "Sentiment and covariance characteristics," International Review of Financial Analysis, Elsevier, vol. 86(C).

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2608.01544. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: https://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.