Jianping Mei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Jianping Mei has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Michael Moses
Beautiful Asset Advisors LLC, New York, USA
3 shared publications Anthony Saunders
1 shared publication- Harrison Hong
Princeton University
1 shared publication - Ilan Kremer
University of Warwick and The Hebrew University of Jerusalem
1 shared publication - Jan Waelty
University of Zürich
1 shared publication - Jeffrey D. Kubik
Syracuse University
1 shared publication
Latest Publications
- Open Access
Deep Learning for Art Market Valuation
We study how deep learning can improve valuation in the art market by incorporating the visual content of artworks into predictive models. Using a large repeated-sales dataset from major auction houses, we benchmark classical hedonic regressions and tree-based methods against modern deep architectures, including multi-modal models that fuse tabular and image data. We find that while artist identity and prior transaction history dominate overall predictive power, visual embeddings provide a distinct and economically meaningful contribution for fresh-to-market works where historical anchors are absent. Interpretability analyses using Grad-CAM and embedding visualizations show that models attend to compositional and stylistic cues. Our findings demonstrate that multi-modal deep learning delivers significant value precisely when valuation is hardest, namely first-time sales, and thus offers new insights for both academic research and practice in art market valuation.
Open AccessDeep Learning for Art Market Valuation
We study how deep learning can improve valuation in the art market by incorporating the visual content of artworks into predictive models. Using a large repeated-sales dataset from major auction houses, we benchmark classical hedonic regressions and tree-based methods against modern deep architectures, including multi-modal models that fuse tabular and image data. We find that while artist identity and prior transaction history dominate overall predictive power, visual embeddings provide a distinct and economically meaningful contribution for fresh-to-market works where historical anchors are absent. Interpretability analyses using Grad-CAM and embedding visualizations show that models attend to compositional and stylistic cues. Our findings demonstrate that multi-modal deep learning delivers significant value precisely when valuation is hardest, namely first-time sales, and thus offers new insights for both academic research and practice in art market valuation.
- 17 August 2022
- Published by Springer Nature in Journal of Cultural Economics
- Vol. 47 (2) , 279-301
Empirical evidence of anchoring and loss aversion from art auctions
- 17 August 2022
- Published by Springer Nature in Journal of Cultural Economics
- Vol. 47 (2) , 279-301
Empirical evidence of anchoring and loss aversion from art auctions
- Open Access
- 20 April 2022
- Published by Springer Nature in Journal of Cultural Economics
- Vol. 47 (3) , 513-545
Residual variance and asset pricing in the art market
In this paper, we compute residual variance of art prices to examine asset pricing in contemporary art market. Our empirical work shows a few interesting results. First, we discover that the residual variance is significantly and positively related to the average price level achieved by an artist. Second, the residual variance has additional explanatory power in terms of how often the artist’s works are cited and exhibited, even after we control for artist fixed (reputation) effects. Third, collectors tend to value more those artworks with higher residual variance. Artworks by those artists with high residual variance tend to outperform the market within and out of sample. One possible explanation of our results is that residual variance could be a proxy for creative risk taking by contemporary artists. The most creative artists dare to take more risks, which results in higher residual price volatility of their artworks.
- 20 April 2022
- Published by Springer Nature in Journal of Cultural Economics
- Vol. 47 (3) , 513-545
Open AccessResidual variance and asset pricing in the art market
In this paper, we compute residual variance of art prices to examine asset pricing in contemporary art market. Our empirical work shows a few interesting results. First, we discover that the residual variance is significantly and positively related to the average price level achieved by an artist. Second, the residual variance has additional explanatory power in terms of how often the artist’s works are cited and exhibited, even after we control for artist fixed (reputation) effects. Third, collectors tend to value more those artworks with higher residual variance. Artworks by those artists with high residual variance tend to outperform the market within and out of sample. One possible explanation of our results is that residual variance could be a proxy for creative risk taking by contemporary artists. The most creative artists dare to take more risks, which results in higher residual price volatility of their artworks.
- 28 January 2015
- Published by Wiley in The RAND Journal of Economics
- Vol. 46 (1) , 186-216
Ordering, revenue and anchoring in art auctions
We estimate the effect of ordering by value on revenues in sequential art auctions held by Sotheby's and Christie's. We exploit a pre determined rotation of which of these two houses holds their auction first during auction week in New York City. When the house that goes first has relatively expensive paintings compared to the other house, we find that the sale premium for the week is around 21% higher relative to the mean sale premium, and the fraction of paintings sold during the week is around 11% higher. We provide evidence that this is due to an anchoring effect.
- 28 January 2015
- Published by Wiley in The RAND Journal of Economics
- Vol. 46 (1) , 186-216
Ordering, revenue and anchoring in art auctions
We estimate the effect of ordering by value on revenues in sequential art auctions held by Sotheby's and Christie's. We exploit a pre determined rotation of which of these two houses holds their auction first during auction week in New York City. When the house that goes first has relatively expensive paintings compared to the other house, we find that the sale premium for the week is around 21% higher relative to the mean sale premium, and the fraction of paintings sold during the week is around 11% higher. We provide evidence that this is due to an anchoring effect.
- 1 March 1994
- Published by JSTOR in Journal of Risk and Insurance
- Vol. 61 (1) , 12-32
The Time-Variation of Risk Premiums on Insurer Stocks
- 1 March 1994
- Published by JSTOR in Journal of Risk and Insurance
- Vol. 61 (1) , 12-32
The Time-Variation of Risk Premiums on Insurer Stocks