Data Feeds (API)

Data Feeds (API)

Platform Access

Our flexible, open data and software solutions can be implemented across the portfolio lifecycle as data feeds serving different workflows in the organization. The API provides access to our unique IP based corporate analytics dataset of more than 700,000 companies on the basis of more than 112 million patents, 220 million scholarly articles and 115 million source code repositories, all matched with public and private corporate data worldwide. Almost all patents, scholarly work and open source ever created digitally. A dedicated expert team verifies and validates all the records in our database to provide a maximum level of validity. Indicators from top universities (Harvard, University of California, University of Hong Kong) and renowned institutions (OECD, NBER) have been implemented to provide unparalleled IP analytics.


Smart beta for trading and portfolio management.


Patent and IP data matched with companies from 65 stock exchanges.


Indicators providing valuable information about companies’ ability and efficiency to innovate.


Industry-leading expertise in delivering real-time data feeds.


Measuring past R&D performance as a predictor of successfully converting R&D expenses into sales revenues. Implementation of the paper “Misvaluing Innovation” by Lauren Cohen, Harvard Business School and NBER, Karl Diether, Tuck School of Business at Dartmouth College and Christopher Malloy, Harvard Business School and NBER.


In this paper we demonstrate that firm-level innovation is predictable, persistent, and relatively simple to compute, and yet the stock market ignores the implications of publicly available information when setting prices. Our approach is based on the simple idea that some firms are likely to be skilled at certain activities, and some are not, and this skill may be persistent over time. Hence, past track records associated with a given activity represent a straightforward way to gauge the future prospects of firms. Using this idea as the starting point for our analysis, we examine the predictability of firm-level R&D track records for future returns and future real outcomes. We show that despite the uncertainty typically associated with R&D investment, substantial return predictability exists by exploiting the information in these firm-level track records. We find that a long-short portfolio strategy that takes advantage of the information in past track records yields abnormal returns of 11 percent per annum. In doing so, we add to the growing literature showing that the market appears to underreact to the information contained in R&D investments. Our tests pinpoint a specific channel through which the market under-reacts to firm-level R&D investments by highlighting the importance of the interaction between a successful past track record and current R&D activity.

We show that the firms we classify as high ability based on their past track records also produce tangible results with their research and development efforts. In particular, R&D spending by high ability firms leads to increased numbers of patents, patent citations, and new product innovations by these firms in the future. The same level of R&D investment by low ability firms does not. Additionally, we document that high R&D ability firms that continue to spend substantial amounts on other activities, such as capital expenditures or total expenses as opposed to R&D, do not experience high future returns. These results suggest that our findings are unlikely to be driven by firms that simply anticipate higher sales growth in the future, and hence ramp up R&D and other firm-level activities in advance of sales growth. Rather, our findings are consistent with the idea that the firms we define as high ability are in fact truly skilled at R&D, and that future firm-level innovation by these firms is unanticipated by the market. Given the substantial shift in the funding of research and development from the public sector to the private sector over the past few decades, the extent to which the stock market properly values investments in R&D is increasingly important. Our findings suggest that while R&D investment is indeed associated with considerable uncertainty, it is possible to identify potential winners and losers solely based on publicly available information. The fact that the stock market fails to adequately incorporate this type of information raises important questions about the efficiency of R&D investment in the economy.

We find that the market consistently misvalues innovation in an ex-ante, predictable way. Specifically, the market does not take into account the information in firms’ past R&D abilities. Firms that have been successful in the past and that invest heavily in R&D as a percentage of sales (“GoodR&D” firms) earn substantially higher future stock returns than firms that invest identical amounts in R&D, but that have poor past track records (“BadR&D” firms). A portfolio of GoodR&D firms earns equal- and value-weighted excess returns of 135 basis points per month (t=2.76) and 122 basis points per month (t=2.61), and 4-factor alphas of 90 basis points per month (t=3.11) and 78 basis points per month (t=2.27), respectively. In contrast, the portfolio of firms with poor past track records but that invests the same amount of R&D (BadR&D) earns -15 basis points per month in 4-factor value-weighted alpha (t=0.56). The spread portfolio that takes identical high R&D-level portfolios, but exploits differences in past track records, has a 4-factor alpha of 93 basis points per month (t=2.30) or over 11% per year. Returns to the “GoodR&D” (and spread) portfolios are large and significant in the first year, and then returns remain slightly positive but basically plateau in the second and third years, with no reversal. This suggests that we are not capturing a form of overreaction, but instead that the embedded information regarding innovation that the market is misvaluing is important for fundamental firm value.


Measuring R&D to IP generation efficiacy: Patents/citations scaled by R&D expenditure a positive predictor of future returns. Implementation of the paper “Innovative efficiency and stock returns” from David Hirshleifer, University of California, Po-Hsuan Hsu, s, University of Hong Kong and Dongmei Li, University of California.


We find that firms that are more efficient in innovation on average have higher contemporaneous market valuations and superior future operating performance, market valuation, and stock returns. The relation between innovative efficiency (IE) and operating performance is robust to controlling for innovation-related variables suggested by other studies, such as R&D-to-market equity, significant R&D growth, patent-to-market equity, and change in adjusted patent citations scaled by average total assets. Similarly, the relation between IE and current (and future) market valuation is also robust to a variety of controls. The positive association of IE with subsequent stock returns is robust to controlling for standard return predictions and innovation-related variables.

Empirical factor pricing models, such as the Carhart four-factor model and the investment-based three-factor model, do not fully explain the IE-return relation. Adding the financing-based mispricing factor UMO to these models improves the models’ explanatory power, but substantial and significant abnormal return performance remains. These findings show that the IE effect on returns is incremental to existing return predictors and cannot be explained by known factors (risk or mispricing). Further analyses show that proxies for investor inattention and valuation uncertainty are associated with stronger ability of IE measures to predict returns. These findings provide further support for psychological bias or constraints contributing to the IE-return relation. The high Sharpe ratios of the two Efficient Minus Inefficient (EMI) factors also suggest this relation is not entirely explained by rational pricing. Finally, regardless of the source of the effect, the heavy weight of the EMI factors in the tangency portfolio suggests that innovative efficiency captures pricing effects above and beyond those captured by the other well-known factors and other innovation effects, which focus on either innovative input or output separately. The fact that the mispricing factor partly helps explain the innovative efficiency effect suggests that there is commonality in mispricing across firms associated with innovative efficiency. Such commonality could arise, for example, if investors do not fully impound news about the correlated shifts in innovative efficiency that are driven by technological shifts. This is consistent with behavioral models in which there is commonality in mispricing (Daniel, Hirshleifer, and Subrahmanyam, 2001; Barberis and Shleifer, 2003). As a policy matter, if capital markets fail to reward firms that are more efficient at innovation, there will be potential misallocation of resources in which firms that are highly effective at innovation are undercapitalized relative to firms that are less effective at innovating. Our findings suggest that investors should direct greater attention to innovative efficiency and that innovative efficiency can be a useful input for firm valuation.

Average monthly size-adjusted portfolio return net of the one-month Treasury bill rate (excess returns) increases monotonically with IE for both IE measures. Specifically, for Patents/RDC, the monthly size-adjusted excess returns on the low, middle, and high IE portfolios are 49 basis points (t 1⁄4 1.48), 86 basis points (t 1⁄4 2.78), and 90 basis points (t 1⁄4 2.79), respectively. For Citations/RD, the monthly size-adjusted excess returns on the low, middle, and high IE portfolios are 59 basis points (t1⁄41.86), 81 basis points (t1⁄42.78), and 85 basis points (t 1⁄4 2.65), respectively. Furthermore, the return spread between the high and low IE portfolios is significant at the 1% level for both IE measures (unreported test).


Measuring IP strength by number of forward citations and other quality criteria. Implementation of methods from the paper “Measuring Patent Quality” from Mariagrazia Squicciarini, Hélène Dernis and Chiara Criscuolo, OECD.


The proposed patent quality measures aim to facilitate analysis both at the level of the individual patent and at the aggregate patent portfolio level. They are intended to help addressing a number of policy- relevant questions, for example, related to: firms innovation strategies and performance; enterprise dynamics, including the drivers of enterprise creation and of mergers and acquisitions; the determinants of productivity; the financing of innovative enterprises; the output of R&D activities and the returns to R&D investments; the depreciation of R&D; the output of universities and of public research organizations.


Based on measuring technological impact by capturing forward citations of AI-IP relative to industry peers, LSTM recurrent neural network models to predict fair market value based on IP and fundamentals and corporate fundamentals.


Is now the right time to buy a stock? Is this stock already overvalued and I should sell it? Traders are asking themselves these questions every day. We can provide more insights: Correlations of up to 0.99 between IP based fair value (“IPI”) and stock prices are strong indicators for future trend direction changes. This provides unique smart beta to your trading decisions – based on research from renowned universities: At the heart of the Trading Signals API is the assimilation of both proprietary and external research to create real-time indicators pertaining to IP and intangible assets. These indicators provide a critical framework for our smart beta and trade analyzer applications, in addition to the real-time alerts flagging stock price discrepancies vs. the IPI.

Corporate Patents API

API level access to our unique IP based corporate analytics dataset of more than 700,000 companies on the basis of more than 110 million patents, 220 million scholarly articles and 115 million source code repositories, all matched with public and private corporate data worldwide. Basically almost all patents, scholarly work and open source ever created digitally.


Access all patents, including title, abstract, status, patent family, family size for an individual corporation (including its subsidiaries). The data feed also includes OECD recommended methods to measure the strength of each patent, also considering its impact and current age. A dedicated expert team verifies and validates the records in our database to provide a maximum level of validity. Patent search can also be conducted horizontally, by vertical, industry, sector or individual natural language search-based queries on the patents title or abstract. This allows sector analytics and positioning relative to peers.

Expertise Makes The Difference.

Get in touch and request a demo