Artwork price index compilation method and device based on expanded sample matching

Abstract

The invention discloses an expansion sample matching-based artwork price index compilation method and device. The method comprises the following steps of: separating and quantifying all features of each artwork; all artworks are subjected to sample grouping according to a predetermined condition, and only any two artwork samples in adjacent time are matched to form a repeated transaction sample pair; constructing a repeated transaction model equation by performing difference on a preset feature price model, and then inputting expanded repeated transaction pair data to calculate an artwork transaction time influence coefficient; and performing index processing on the artwork transaction time influence coefficient to obtain an artwork price index. The method can effectively solve the problem of artwork heterogeneity, the estimation of the artwork price index has higher accuracy and effectiveness, the index trend is more obvious, the volatility is lower, the comprehensive quality is higher, and the method has a better application prospect in the artwork market.

Description

Technical Field

[0001] The present invention relates to the field of artwork transaction technology, and in particular to a method and device for compiling an artwork price index based on expanded sample matching. Background Art

[0002] At present, the art price index on the market can be roughly divided into the following three types according to specific technical routes:

[0003] (1) Average index:

[0004] The average index is the simplest art price index. It reflects the overall operation of the art market by calculating the average or weighted average of art market prices over a period of time. The advantage of the average index is that the calculation method is simple and easy to operate, and the requirements for data conditions and calculation conditions for index calculation are relatively low. However, this method belongs to a non-homogeneous art price index method and cannot overcome the heterogeneity problem naturally existing in the art market. Therefore, the average index has certain errors in reflecting the price changes in the art market and can only be used as a tool to intuitively describe the operation of the market. Among them, the Artron Auction Index is an average index.

[0005] (2) Hedonic price index:

[0006] The hedonic price index is a widely used art price index method that compiles the art price index by measuring the characteristic prices of the physical and cultural characteristics of the artwork. A relatively stable and mature theoretical framework and technical operation methods have gradually been formed for the hedonic price model. The hedonic price model is widely used in the study of heterogeneous commodities. In theory, the hedonic price index can fully adjust the heterogeneity of sample observations and evaluate the accuracy and effectiveness of the index calculation results through econometric regression. However, in actual operation, since it is impossible to observe or measure all the characteristics of the artwork, or it is difficult to quantify its characteristics, the hedonic price index always has a certain estimation bias in the econometric regression model, which reduces the accuracy of the hedonic price index. Among them, the Artprice Artwork Index is a hedonic price index.

[0007] (3) Repeat transaction index:

[0008] The repeat transaction index uses multiple transaction data of the same sample in different periods to calculate the art price index, which is also a widely used art price index method. The repeat transaction index method assumes that the characteristics of the artwork and its characteristic price do not change over time and do not need to be observed. It only calculates the average price change of the art market by observing the price changes of each artwork sample in two transactions. The calculation of the repeat transaction index only relies on samples that have been traded multiple times, and the proportion of such samples in all art market transactions is relatively low. Therefore, there is a very obvious sample selection bias in the calculation of the repeat transaction index. Among them, the Mei&Moses index is a repeat transaction index.

[0009] Therefore, the three existing technical routes for constructing art price indices have their own shortcomings, making it impossible to obtain an art price index with a more stable trend, lower volatility and better overall quality.

[0010] In view of this, it is necessary to provide a method and device for compiling an art price index based on expanded sample matching to overcome the above-mentioned defects. Summary of the invention

[0011] The purpose of the present invention is to provide a method and device for compiling an artwork price index based on expanded sample matching, aiming to solve the problem of artwork heterogeneity and construct an artwork price index with a more stable trend, lower volatility and better overall quality.

[0012] In order to achieve the above object, the present invention provides a method for compiling an artwork price index based on expanded sample matching, comprising:

[0013] Step S10: Processing the artwork auction data provided by various auction companies, and separating and quantifying all the features of each artwork;

[0014] Step S20: grouping all artworks into samples according to predetermined conditions, and then sorting all artwork samples in the same group by transaction time, and matching only any two artwork samples in adjacent time periods to form a repeated transaction sample pair, thereby obtaining expanded repeated transaction pair data;

[0015] Step S30: constructing a repeated transaction model equation by differentiating the preset characteristic price model, and then inputting the expanded repeated transaction pair data to calculate the artwork transaction time influence coefficient;

[0016] Step S40: Indexing the time impact coefficient of the artwork transaction to obtain a dimensionless artwork price index that only reflects the average price change trajectory of the artwork market.

[0017] In a preferred embodiment, in step S20, if there is no transaction in the current period, artwork samples that are closest to each other in the two previous and subsequent transaction periods are selected to form a repeated transaction pair sample.

[0018] In a preferred embodiment, the step S30 includes:

[0019] Define that artwork samples u and v constitute a repeated transaction pair q, and the repeated transaction model equation is as follows:

[0020]

[0021] Where b and s are the buying period and selling period of artwork sample i, respectively. qus is the transaction price of artwork sample u in repeated transaction pair q in selling period s, P qvb is the transaction price of the artwork sample v in the repeated transaction pair q in the buying period b, α j is the characteristic price corresponding to each artwork feature, X qusj is the artwork feature j of the artwork sample u in the repeated transaction pair q in the selling period s, X qvbj is the artwork feature j of the artwork sample v in the repeated transaction pair q in the buying period b, ∈ quvsb is the random error of repeated transactions on q; k The influence coefficient of art transaction time obtained from the repeated transaction model equation.

[0022] In a preferred embodiment, in step S40, the artwork transaction time impact coefficient is indexed; the indexation formula is as follows:

[0023] Among them, I k is the art price index of the kth period, and it is assumed that the index of the first period is 100.

[0024] In a preferred embodiment, the artwork features include typicality of subject matter, composition layout, and size of the artwork.

[0025] The present invention also provides a device for compiling an artwork price index based on expanded sample matching, comprising:

[0026] The feature acquisition and quantification module is used to process the art auction data provided by various auction companies and separate and quantify all the features of each artwork;

[0027] The sample matching and grouping module is used to group all artworks into samples according to predetermined conditions, and then sort all artwork samples in the same group by transaction time, and only match any two artwork samples in adjacent time periods to form a repeated transaction sample pair, thereby obtaining expanded repeated transaction pair data;

[0028] The influence coefficient calculation module is used to construct a repeated transaction model equation by differentiating the preset characteristic price model, and then input the expanded repeated transaction pair data to calculate the influence coefficient of the artwork transaction time;

[0029] The price index calculation module is used to index the time impact coefficient of the artwork transaction to obtain a dimensionless artwork price index that only reflects the average price change trajectory of the artwork market.

[0030] The method and device for compiling an art price index based on expanded sample matching provided by the present invention obtains expanded repeated transaction pair data through sample grouping and based on expanded repeated transaction sample matching, so that all art samples in the group can eliminate most of the unmeasurable features outside the group through differential, leaving only a small amount of characteristic attributes that are convenient for observation to be controlled, thereby improving the estimation accuracy and effectiveness of the model transaction time coefficient, thereby combining the method advantages of the traditional characteristic price model and the classic repeated sales model, being able to avoid the application limitations of the classic repeated sales model, and reducing the deviation caused by the omitted variable problem in the characteristic price model. Therefore, the present invention can effectively solve the problem of artwork heterogeneity, the estimation of the artwork price index has higher accuracy and effectiveness, the index trend is more obvious, the volatility is lower, the overall quality is higher, and it has good application prospects in the artwork market. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 A flow chart of a method for compiling an artwork price index based on expanded sample matching provided by the present invention;

[0033] Figure 2 A comparison chart of the art price index calculated by various methods in an exemplary embodiment;

[0034] Figure 3 A framework diagram of the device for compiling an artwork price index based on expanded sample matching provided by the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and beneficial technical effect of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be understood that the specific implementation methods described in this specification are only for explaining the present invention, not for limiting the present invention.

[0036] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0037] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0038] Embodiment 1

[0039] In an embodiment of the present invention, a method for compiling an art price index based on expanded sample matching is provided, that is, a new art price index construction method is proposed, which can be called a repeated transaction art price index model based on expanded repeated transaction sample matching, and is intended to solve the limitations of the classic repeat sales model and the characteristic price model in the art transaction market. The method of this model combines the advantages of the characteristic price model and the classic repeat sales model, can avoid the application limitations of the classic repeat sales model, and reduce the deviation caused by the omitted variable problem in the characteristic price model.

[0040] like Figure 1 As shown, the method for compiling an artwork price index based on expanded sample matching includes steps S10-S40.

[0041] Step S10: Process the artwork auction data provided by various auction companies, and separate and quantify all the features of each artwork.

[0042] In this step, in order to ensure the authenticity and high data quality of the original data source. Art auction data can be provided directly by the auction company or obtained through data published on the official website. It should be noted that according to the characteristic price theory, artworks have decomposable characteristics (attributes) such as typicality of subject matter, composition layout, and size of the work, and can be quantified by appropriate methods. Various characteristics have their own characteristic prices. The price of an artwork can be expressed as the sum of the product of the number of each feature and its characteristic price, that is, the characteristic price equation. The characteristic price equation is as follows:

[0043] Among them, P iis the transaction price of artwork sample i, X j are different artwork features of artwork sample i, α j is the characteristic price corresponding to each artwork feature; D k is the time dummy variable of the artwork sample i in the kth auction period, which is used to estimate the change of the corresponding artwork price over time; β k is the time influence coefficient of the artwork transaction in period k, ∈ i is the random error of artwork sample i.

[0044] Furthermore, the classic repeated transaction model can be obtained by differentiating the characteristic price equation. Assuming that the sample of artworks that are traded will not undergo significant characteristic changes between two transactions, the repeated transaction rule does not need to observe the characteristic variables of artworks. The two transactions before and after the artwork sample i are combined into a repeated transaction pair, and the difference in the price logarithm corresponding to the selling period and the buying period is used to regress the transaction time variable. The corresponding regression equation is as follows:

[0045]

[0046] Where b and s are the buying period and selling period of artwork sample i, respectively, ∈ ik is the random error of the kth period; k is the influence coefficient of artwork transaction time obtained through the regression equation.

[0047] In this embodiment, the characteristics of artworks include typicality of subject matter, composition layout, size of artworks, etc. Specifically, the data source for calculating the artwork price index should be authentic, reliable, and easy to obtain. The data published on the official website of each auction company is usually used. The principles and methods used for data cleaning should meet the requirements of being able to separate and quantify all the characteristics (attributes) of artworks by appropriate methods. For example, for the two characteristics of the typicality of subject matter and composition layout of artworks, the characteristic values ​​may be quantified by taking the average value after multiple industry experts independently score back to back. The size feature of the work can be segmented to quantify the characteristic value by its numerical value. In addition, the transaction price of the artwork should be greater than zero, that is, there should be an auction record of the transaction.

[0048] Step S20: All artworks are grouped into samples according to predetermined conditions, and then all artwork samples in the same group are sorted by transaction time, and only any two artwork samples in adjacent time are matched to form a repeated transaction sample pair, thereby obtaining expanded repeated transaction pair data.

[0049] The principle of artwork sample expansion matching is to select a suitable group so that all artwork samples in the group can eliminate most of the unmeasurable features outside the group through differentiation, leaving only a small number of easy-to-observe characteristic attributes to be controlled, thereby improving the estimation accuracy and effectiveness of the model transaction time coefficient. Artwork sample expansion matching is divided into two steps: one is grouping by conditions, and the other is expansion sample matching.

[0050] Specifically, the conditional grouping step includes: selecting a sample group with a clear range according to certain conditions, matching samples within the group, and not matching samples outside the group with samples within the group. Since the more refined the grouping selection, the higher the homogeneity of the samples within the group, the better the grouping is. Therefore, the calculation accuracy of the art price index is largely determined by the quality of the grouping. The quality of feature grouping will directly affect the calculation accuracy of the index. Therefore, feature grouping should be strongly related to the business status and data situation, and carefully designed. For example, from industry experience and data observation, when the typicality of the subject matter-composition layout-work size is used as a group, the art samples within the group will have many similar characteristics (such as subject matter popularity, timeliness, degree of innovation of artistic themes, etc.), and there are only a few micro differences such as the social status of the creator, the integrity of the work, and the publication of the work.

[0051] The expanded sample matching step includes: after sorting all artwork samples in the same group by transaction time, only any two samples at adjacent times are matched to form a sample pair. If no transaction occurs in the current period, the samples of the two periods closest to the current period are paired to expand the sample size of artworks. The matching process is carried out in pairs, so the sample size increases at a quadratic rate. According to the law of large numbers and the central limit theorem, the sample size determines the accuracy of the model estimation, and a large sample size can improve the effectiveness of the model estimation results.

[0052] For example, after selecting a group, arrange the artwork samples in the group in order of transaction time, and any two adjacent artwork samples can form a repeated transaction pair. For example, if artwork A has transaction records in the 2020 spring auction and the 2020 autumn auction, and artwork B has transaction records in the 2020 spring auction, they can form two repeated transaction pairs: (artwork A-artwork A) and (artwork B-artwork A). If there is no transaction in the current period, the artwork samples closest to the two transaction periods are selected to form a repeated transaction pair. For example, artwork D and artwork E have transaction records in the 2018 autumn auction and the 2019 autumn auction respectively, and no artworks are traded in the 2019 spring auction, then (artwork D-artwork E) forms a repeated transaction pair.

[0053] Step S30: Construct a repeated transaction model equation by differentiating the preset characteristic price model, and then input the expanded repeated transaction pair data to calculate the art transaction time impact coefficient.

[0054] In the actual operation of the classic repeated transaction method, the samples of artworks that have been traded more than twice are significantly less than the samples of artworks that have been traded only once, resulting in sample selection bias. In order to avoid such application limitations, the present invention adopts an expanded sample matching method to significantly increase the number of repeated transaction pairs and construct a new model equation. Specifically, step S30 includes: constructing a repeated transaction model equation by combining the above regression equation with an expanded sample matching method: defining that artwork samples u and v constitute a repeated transaction pair q, and the repeated transaction model equation is as follows:

[0055] Among them, P qus is the transaction price of artwork sample u in repeated transaction pair q in selling period s, P qvb is the transaction price of the artwork sample v in the repeated transaction pair q in the buying period b, X qusj is the artwork feature j of the artwork sample u in the repeated transaction pair q in the selling period s, X qvbj is the artwork feature j of the artwork sample v in the repeated transaction pair q in the buying period b, ∈ quvsb is the random error of repeated transactions on q; k The influence coefficient of art transaction time obtained from the repeated transaction model equation.

[0056] Therefore, the expanded repeated transaction pairs data is brought into the above repeated transaction model equation to calculate the time effect coefficient of art transaction. At the same time, the estimation effect or quality of the model is evaluated, which is specifically reflected in two aspects: on the one hand, the significance of the coefficient estimation results, and on the other hand, the overall goodness of fit of the model. If the model estimation effect does not meet the requirements, the influence of factors such as the feature separation or cleaning effect of the sample data, or feature grouping, should be considered.

[0057] Step S40: Indexing the time impact coefficient of artwork transactions to obtain a dimensionless artwork price index that only reflects the average price change trajectory of the artwork market.

[0058] After determining the model's art transaction time impact coefficient, you can bring in the art price index calculation formula (i.e., indexation formula) to complete the construction of the art price index. The indexation formula is as follows:

[0059] Among them, I k is the art price index of the kth period, and it is assumed that the index of the first period is 100.

[0060] In order to help those skilled in the art understand the beneficial effects of the method of the present invention more intuitively and accurately, an exemplary embodiment will be used below to illustrate the advantages of the art price index model provided by the present method over the three traditional index technology methods mentioned in the background technology section.

[0061] Using the works and transaction data of contemporary Chinese painting and calligraphy artists in the Artron Chinese Art Library database owned by the applicant of the present invention, the art price index model proposed by the present invention is designed to be grouped into the typicality of the subject matter, the composition layout, and the size of the work, and the art price index is obtained by trial calculation. It is compared with the art price index calculated by the average method, the characteristic price method, and the classic repeated transaction method. The results are as follows: Figure 2 as shown.

[0062] from Figure 2 It can be observed intuitively that the fluctuation of the repeated transaction index of the expanded sample is relatively smooth, while the other three indices are more obvious. The two repeated transaction indices are relatively close, and both are far away from the characteristic price index. At the significance level of 0.05, the model estimation results of the characteristic price index, the classic repeated transaction index and the repeated transaction index of the expanded sample are all significantly different, and the adjusted R-squares are 0.965, 0.738 and 0.969 respectively. This confirms the positive regulatory effect of expanding the number of sample matches of repeated transactions on the accuracy of index estimation through carefully designed grouping.

[0063] Therefore, the present invention constructs an art price index model by expanding the number of matching pairs of repeated art transactions. Compared with the characteristic price index and the average index, the present invention can effectively solve the problem of art heterogeneity. The estimation of the art price index has higher accuracy and effectiveness, more obvious index trend, lower volatility, higher comprehensive quality, and has good application prospects in the art market.

[0064] Embodiment 2

[0065] The present invention provides an art price index compilation device 100 based on expanded sample matching, which is used to combine the advantages of the characteristic price model and the classic repeat sales model, can avoid the application limitations of the classic repeat sales model, and reduce the deviation caused by the omitted variable problem in the characteristic price model. It should be noted that the implementation principle and specific implementation method of the art price index compilation device 100 based on expanded sample matching can refer to the above-mentioned art price index compilation method based on expanded sample matching, so it will not be repeated below.

[0066] like Figure 3 As shown, the art price index compilation device 100 based on expanded sample matching includes:

[0067] The feature acquisition and quantification module 10 is used to process the artwork auction data provided by various auction companies, and separate and quantify all the features of each artwork;

[0068] The sample matching and grouping module 20 is used to group all artworks into samples according to predetermined conditions, and then sort all artwork samples in the same group by transaction time, and only match any two artwork samples in adjacent time periods to form a repeated transaction sample pair, thereby obtaining expanded repeated transaction pair data;

[0069] The influence coefficient calculation module 30 is used to construct a repeated transaction model equation by differentiating the preset characteristic price model, and then input the expanded repeated transaction pair data to calculate the artwork transaction time influence coefficient;

[0070] The price index calculation module 40 is used to index the time influence coefficient of artwork transaction to obtain a dimensionless artwork price index that only reflects the average price change trajectory of the artwork market.

[0071] In summary, the method and device for compiling an art price index based on expanded sample matching provided by the present invention obtains expanded repeated transaction pair data through sample grouping and based on expanded repeated transaction sample matching, so that all art samples in the group can eliminate most of the unmeasurable features outside the group through differential, leaving only a small number of characteristic attributes that are convenient for observation to be controlled, thereby improving the estimation accuracy and effectiveness of the model transaction time coefficient, thereby combining the method advantages of the traditional characteristic price model and the classic repeat sales model, avoiding the application limitations of the classic repeat sales model, and reducing the deviation caused by the omitted variable problem in the characteristic price model. Therefore, compared with the characteristic price index and the average price index, the repeated transaction model equation model of the present invention constructs an index that shows a more stable trend, lower volatility and better overall quality.

[0072] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0073] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0074] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0075] In the embodiments provided by the present invention, it should be understood that the disclosed systems or devices / terminal equipment and methods can be implemented in other ways. For example, the system or device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the system or unit can be electrical, mechanical or other forms.

[0076] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0077] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0078] The present invention is not limited to what is described in the specification and implementation modes, and therefore additional advantages and modifications can be easily realized by those skilled in the art. Therefore, without departing from the spirit and scope of the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details, representative devices, and illustrative examples shown and described herein.

Claims

1. A method for compiling an art price index based on expanded sample matching, characterized in that: include: Step S10: Processing the artwork auction data provided by various auction companies, and separating and quantifying all the features of each artwork; Step S20: grouping all artworks into samples according to predetermined conditions, and then sorting all artwork samples in the same group by transaction time, and matching only any two artwork samples in adjacent time periods to form a repeated transaction sample pair, thereby obtaining expanded repeated transaction pair data; Step S30: constructing a repeated transaction model equation by differentiating the preset characteristic price model, and then inputting the expanded repeated transaction pair data to calculate the artwork transaction time influence coefficient; Step S40: Indexing the time impact coefficient of the artwork transaction to obtain a dimensionless artwork price index that only reflects the average price change trajectory of the artwork market.

2. The method for compiling an art price index based on expanded sample matching according to claim 1, characterized in that: In step S20, if there is no transaction in the current period, the artwork samples that are closest to each other in the two previous and subsequent transaction periods are selected to form a repeated transaction pair sample.

3. The method for compiling an art price index based on expanded sample matching according to claim 1, characterized in that: The step S30 comprises: Define that artwork samples u and v constitute a repeated transaction pair q, and the repeated transaction model equation is as follows: Where b and s are the buying period and selling period of artwork sample i, respectively. qus is the transaction price of artwork sample u in repeated transaction pair q in selling period s, P qvb is the transaction price of the artwork sample v in the repeated transaction pair q in the buying period b, α j is the characteristic price corresponding to each artwork feature, X qusj is the artwork feature j of the artwork sample u in the repeated transaction pair q in the selling period s, X qvbj is the artwork feature j of the artwork sample v in the repeated transaction pair q in the buying period b, ∈ quvsb is the random error of repeated transactions on q; k The influence coefficient of art transaction time obtained from the repeated transaction model equation.

4. The method for compiling an artwork price index based on expanded sample matching according to claim 3, characterized in that: In the step S40, the artwork transaction time influence coefficient is indexed; the indexation formula is as follows: Among them, I k is the art price index of the kth period, and it is assumed that the index of the first period is 100.

5. The method for compiling an art price index based on expanded sample matching according to claim 1, characterized in that: Features of artworks include typicality of subject matter, composition and layout, and size of the work.

6. A device for compiling an art price index based on expanded sample matching, characterized in that: include: The feature acquisition and quantification module is used to process the art auction data provided by various auction companies and separate and quantify all the features of each artwork; The sample matching and grouping module is used to group all artworks into samples according to predetermined conditions, and then sort all artwork samples in the same group by transaction time, and only match any two artwork samples in adjacent time periods to form a repeated transaction sample pair, thereby obtaining expanded repeated transaction pair data; The influence coefficient calculation module is used to construct a repeated transaction model equation by differentiating the preset characteristic price model, and then input the expanded repeated transaction pair data to calculate the influence coefficient of the artwork transaction time; The price index calculation module is used to index the time impact coefficient of the artwork transaction to obtain a dimensionless artwork price index that only reflects the average price change trajectory of the artwork market.

Images