Abstract
The article addresses questions on how to form decisions, and how approaches founded on artificial intelligence can help us to improve them. It does so by discussing three exemplary case studies that are based on Niederreiter (Essays on contest experiments and supervised learning in the pharmaceutical industry, PhD thesis, IMT School for Advanced Studies Lucca, 2020) and complement this work. Each case study is a self-contained stream of work written such that different backgrounds, methodologies, and results are explained in sufficient depth to provide a base for future research. The first case study applies game theoretical learning models to laboratory data to understand how people learn in different competitive environments. The second case study uses a novel classification approach to identify latent behavioural types in such environments. The third case study employs a supervised learning method to obtain easily interpretable decision rules that aid at successfully classifying the outcome of clinical trials. Overall, the article advocates the importance of uniting approaches that originate outside mainstream economics but have the potential to broaden its portfolio and its appeal.
Similar content being viewed by others
Notes
The first period is dropped since it does not include information on the previous round. Two players are removed since their choices did not vary sufficiently over time to estimate fixed effects. All effort related information is scaled down by a factor of 100 to align the range of all variables used.
The myopic best response function to opponents efforts is concave and thus better approximated by a polynomial of 2nd order.
For reasons of brevity table 6 for the three-player treatment and 7 for the five-player treatment are reported in the supplementary material.
For better readability, a pharmaceutical project in this case study refers to a new molecular entity (NME) monitored by the FDA that reports at least one drug with indication status in the US, the worldwide biggest geographical market for pharmaceutical products regulated by a single authority (Kyle 2006). An NME that is filed for different indications implies different projects based on this definition.
Sensitivity is the ratio of all correctly classified successes divided by all actual successes. Specificity is the ratio of all correctly classified failures divided by all actual failures. Accuracy is the ratio of all correctly classified observations over all observations. Looking at the accuracy as an overall measure might be misleading in the case that there are much more observations of one type than of the other, especially when the classification performance of both successes and failures is of interest.
It is most commonly required that three clinical trial stages (named phase I,II,III) are successfully passed before a company can file for a drug’s approval. Yet, certain trials are assigned intermediate stages such as phase I/II and also phase IV trials are sometimes carried out. Here we focus on the three main categories.
References
Abadie A, Kasy M (2019) Choosing among regularized estimators in empirical economics: the risk of machine learning. Rev Econ Stat 101(5):743–762
Alós-Ferrer C, Ritschel A (2018) The reinforcement heuristic in normal form games. J Econ Behav Organ 152:224–234
Arora S, Doshi P (2021) A survey of inverse reinforcement learning: challenges, methods and progress. Artif Intell 20:103500
Athey S (2018) The impact of machine learning on economics. The economics of artificial intelligence: an agenda. University of Chicago Press, Chicago, pp 507–547
Athey S (2019) 21. The impact of machine learning on economics. The economics of artificial intelligence. University of Chicago Press, Chicago, pp 507–552
Bao W, Lianju N, Yue K (2019) Integration of unsupervised and supervised machine learning algorithms for credit risk assessment. Expert Syst Appl 128:301–315
Bardsley N, Moffatt PG (2007) The experimetrics of public goods: inferring motivations from contributions. Theor Decis 62(2):161–193
Bardsley N, Cubitt R, Loomes G, Moffatt P, Starmer C, Sugden R (2020) Experimental economics: rethinking the rules. Princeton University Press, Princeton
Bargagli-Stoffi FJ, Niederreiter J, Riccaboni M (2021) Supervised learning for the prediction of firm dynamics. Data science for economics and finance. Springer, Cham, pp 19–41
Behr A, Weinblat J (2017) Default patterns in seven EU countries: a random forest approach. Int J Econ Bus 24(2):181–222
Bigoni M (2010) What do you want to know? Information acquisition and learning in experimental cournot games. Res Econ 64(1):1–17
Bigoni M, Fort M (2013) Information and learning in oligopoly: an experiment. Games Econom Behav 81:192–214
Bonhomme S, Manresa E (2015) Grouped patterns of heterogeneity in panel data. Econometrica 83(3):1147–1184
Boosey L, Brookins P, Ryvkin D (2017) Contests with group size uncertainty: experimental evidence. Games Econom Behav 105:212–229
Bordt S Farbmacher H (2018) Estimating individual heterogeneity in repeated public goods experiments. mimeo
Bosch-Domènech A, Montalvo JG, Nagel R, Satorra A (2010) A finite mixture analysis of beauty-contest data using generalized beta distributions. Exp Econ 13(4):461–475
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Brocas I, Carrillo JD, Wang SW, Camerer CF (2014) Imperfect choice or imperfect attention? Understanding strategic thinking in private information games. Rev Econ Stud 81(3):944–970
Brown GW (1951) Iterative solution of games by fictitious play. Activity Anal Prod Alloc 13(1):374–376
Buehler H, Gonon L, Teichmann J, Wood B (2019) Deep hedging. Quant Financ 19(8):1271–1291
Burbidge R, Trotter M, Buxton B, Holden S (2001) Drug design by machine learning: support vector machines for pharmaceutical data analysis. Comput Chem 26(1):5–14
Camerer C, Ho TH (1999) Experience-weighted attraction learning in normal form games. Econometrica 67(4):827–874
Camerer CF, Ho T-H, Chong J-K (2002) Sophisticated experience-weighted attraction learning and strategic teaching in repeated games. J Econ Theory 104(1):137–188
Camerer CF, Ho T-H, Chong J-K (2004) A cognitive hierarchy model of games. Q J Econ 119(3):861–898
Casari M, Plott CR (2003) Decentralized management of common property resources: experiments with a centuries-old institution. J Econ Behav Organ 51(2):217–247
Cason TN, Sheremeta RM, Zhang J (2012) Communication and efficiency in competitive coordination games. Games Econom Behav 76(1):26–43
Cason TN, Masters WA, Sheremeta RM (2018) Winner-take-all and proportional-prize contests: theory and experimental results. J Econ Behav Organ 175:314–27
Charpentier A, Elie R, Remlinger C (2021) Reinforcement learning in economics and finance. Comput Econ 20:1–38
Conte A, Hey JD, Moffatt PG (2011) Mixture models of choice under risk. J Econom 162(1):79–88
Cosaert S (2019) What types are there? Comput Econ 53(2):533–554
Dechenaux E, Kovenock D, Sheremeta RM (2015) A survey of experimental research on contests, all-pay auctions and tournaments. Exp Econ 18(4):609–669
Desokey EN, Badr A, Hegazy AF (2017) Enhancing stock prediction clustering using k-means with genetic algorithm. In: 2017 13th international computer engineering conference (ICENCO), pp 256–261. IEEE
DiMasi JA (2001) Risks in new drug development: approval success rates for investigational drugs. Clin Pharmacol Therap 69(5):297–307
DiMasi J, Hermann J, Twyman K, Kondru R, Stergiopoulos S, Getz K, Rackoff W (2015) A tool for predicting regulatory approval after phase ii testing of new oncology compounds. Clin Pharmacol Therap 98(5):506–513
Dimitri N (2017) Bitcoin mining as a contest. Ledger 2:31–37
Dosi G, Marengo L, Fagiolo G (2001) Learning in evolutionary environments. Technical report, LEM Working Paper Series
El-Gamal MA, Grether DM (1995) Are people Bayesian? Uncovering behavioral strategies. J Am Stat Assoc 90(432):1137–1145
Fallucchi F, Renner E, Sefton M (2013) Information feedback and contest structure in rent-seeking games. Eur Econ Rev 64:223–240
Fallucchi F, Luccasen RA, Turocy TL (2019) Identifying discrete behavioural types: a re-analysis of public goods game contributions by hierarchical clustering. J Econ Sci Assoc 5(2):238–254
Fallucchi F, Mercatanti A, Niederreiter J (2020a) Identifying types in contest experiments. Int J Game Theory 20:1–23
Fallucchi F, Niederreiter J, Riccaboni M (2020b) Learning and dropout in contests: an experimental approach. Theory Decis 20:1–34
Feijoo F, Palopoli M, Bernstein J, Siddiqui S, Albright TE (2020) Key indicators of phase transition for clinical trials through machine learning. Drug Discov Today 25(2):414–21
Fischbacher U, Gächter S, Fehr E (2001) Are people conditionally cooperative? Evidence from a public goods experiment. Econ Lett 71(3):397–404
Fischer T, Krauss C (2018) Deep learning with long short-term memory networks for financial market predictions. Eur J Oper Res 270(2):654–669
Fischer JE, Steiner F, Zucol F, Berger C, Martignon L, Bossart W, Altwegg M, Nadal D (2002) Use of simple heuristics to target macrolide prescription in children with community-acquired pneumonia. Arch Pediatr Adolesc Med 156(10):1005–1008
Fraley C, Raftery AE (2002) Model-based clustering, discriminant analysis, and density estimation. J Am Stat Assoc 97(458):611–631
Green L, Mehr DR (1997) What alters physicians’ decisions to admit to the coronary care unit? J Fam Pract 45(3):219–226
Gunnthorsdottir A, Rapoport A (2006) Embedding social dilemmas in intergroup competition reduces free-riding. Organ Behav Hum Decis Process 101(2):184–199
Hay M, Thomas DW, Craighead JL, Economides C, Rosenthal J (2014) Clinical development success rates for investigational drugs. Nat Biotechnol 32(1):40
Ho TH, Camerer CF, Chong J-K (2007) Self-tuning experience weighted attraction learning in games. J Econ Theory 133(1):177–198
Houser D, Keane M, McCabe K (2004) Behavior in a dynamic decision problem: an analysis of experimental evidence using a bayesian type classification algorithm. Econometrica 72(3):781–822
Hughes N (2014) Applying reinforcement learning to economic problems. In: ANU Crawford Phd Conference
Inyang UG, Obot OO, Ekpenyong ME, Bolanle AM (2017) Unsupervised learning framework for customer requisition and behavioral pattern classification. Mod Appl Sci 11:151
Johari SNM, Farid FHM, Nasrudin NAEB, Bistamam NSL, Shuhaili NSSM (2018) Predicting stock market index using hybrid intelligence model. Int J Eng Technol 7:36–9
Konrad KA (2009) Strategy and dynamics in contests. Oxford University Press, Oxford
Krueger AO (1974) The political economy of the rent-seeking society. Am Econ Rev 64(3):291–303
Kruse DL (1992) Profit sharing and productivity: microeconomic evidence from the United States. Econ J 102(410):24–36
Kuhn M, Johnson K (2013) Applied predictive modeling, vol 26. Springer, Berlin
Kurzban R, Houser D (2005) Experiments investigating cooperative types in humans: a complement to evolutionary theory and simulations. Proc Natl Acad Sci 102(5):1803–1807
Kyle MK (2006) The role of firm characteristics in pharmaceutical product launches. Rand J Econ 37(3):602–618
Lee I, Shin YJ (2020) Machine learning for enterprises: applications, algorithm selection, and challenges. Bus Horiz 63(2):157–170
Lehmann EL, Casella G (2006) Theory of point estimation. Springer, Berlin
Lo AW, Siah KW, Wong CH (2019) Machine learning with statistical imputation for predicting drug approvals. Harvard Data Sci Rev
Lu X, Su L (2017) Determining the number of groups in latent panel structures with an application to income and democracy. Quant Econ 8(3):729–760
Mago SD, Samak AC, Sheremeta RM (2016) Facing your opponents: social identification and information feedback in contests. J Conflict Resolut 60(3):459–481
Makin S (2018) The amyloid hypothesis on trial. Last checked on 06 February, 2020
Malik A, Lisa U (2018) World preview 2018, outlook to 2024. Last checked on 12 March, 2019
Martignon L, Vitouch O, Takezawa M, Forste MR (2003) Naive and yet enlightened: From natural frequencies to fast and frugal decision trees. Think Psychol Perspect Reason Judgment Decisi Mak 2:189–211
Masiliunas A (2017) Learning in contests with payoff risk and foregone payoff information. Working Paper
McKinsey&Company (2009) ’and the winner is...’: capturing the promise of philanthropic prizes. Online accessed 14 Feb 2018
Moffatt PG (2021) Experimetrics: a survey. Found Trends Econom 11(1–2):1–152
Mosavi A, Faghan Y, Ghamisi P, Duan P, Ardabili SF, Salwana E, Band SS (2020) Comprehensive review of deep reinforcement learning methods and applications in economics. Mathematics 8(10):1640
Munos B, Niederreiter J, Riccaboni M (2021) Improving the prediction of clinical success using machine learning. medRxiv
Nair BB, Kumar PS, Sakthivel N, Vipin U (2017) Clustering stock price time series data to generate stock trading recommendations: an empirical study. Expert Syst Appl 70:20–36
Niederreiter J (2020) Essays on contest experiments and supervised learning in the pharmaceutical industry. PhD thesis, IMT School for Advanced Studies Lucca
Niederreiter J, Riccaboni M (2021) The impact of product innovation announcements on firm value: evidence from the bio-pharmaceutical industry. Industry and Innovation
Oechssler J, Roomets A, Roth S (2016) From imitation to collusion: a replication. J Econ Sci Assoc 2(1):13–21
Parkins (2017) The world’s most valuable resource is no longer oil, but data. https://www.economist.com/leaders/2017/05/06/the-worlds-most-valuable-resource-is-no-longer-oil-but-data. Last checked on 17 May 2020
Phillips ND, Neth H, Woike JK, Gaissmaier W (2017) Fftrees: a toolbox to create, visualize, and evaluate fast-and-frugal decision trees. Judgm Decis Mak 12(4):344–368
Piotrowski EW, Sładkowski J, Szczypińska A (2010) Reinforced learning in market games. Econophysics and economics of games, social choices and quantitative techniques. Springer, Berlin, pp 17–23
Polonio L, Di Guida S, Coricelli G (2015) Strategic sophistication and attention in games: an eye-tracking study. Games Econom Behav 94:80–96
Press (2019) Amazon saw 15-fold jump in forecast accuracy with deep learning and other AI stats. https://www.forbes.com/sites/gilpress/2019/11/14/amazon-saw-15-fold-jump-in-forecast-accuracy-with-deep-learning-and-other-ai-stats. Last checked on 23 April 2020
Price CR, Sheremeta RM (2011) Endowment effects in contests. Econ Lett 111(3):217–219
Rai AK, Dwivedi RK (2020) Fraud detection in credit card data using unsupervised machine learning based scheme. In: 2020 international conference on electronics and sustainable communication systems (ICESC), pp 421–426. IEEE
Roth AE, Erev I (1995) Learning in extensive-form games: experimental data and simple dynamic models in the intermediate term. Games Econom Behav 8(1):164–212
Ruiz FJ, Athey S, Blei DM et al (2020) Shopper: a probabilistic model of consumer choice with substitutes and complements. Ann Appl Stat 14(1):1–27
Seoane-Vazquez E, Rodriguez-Monguio R, Szeinbach SL, Visaria J (2008) Incentives for orphan drug research and development in the united states. Orphanet J Rare Dis 3(1):1–7
Shachat J, Wei L (2012) Procuring commodities: first-price sealed-bid or English auctions? Mark Sci 31(2):317–333
Sheremeta RM (2010) Experimental comparison of multi-stage and one-stage contests. Games Econom Behav 68(2):731–747
Sheremeta RM (2011) Contest design: an experimental investigation. Econ Inq 49(2):573–590
Sheremeta RM (2013) Overbidding and heterogeneous behavior in contest experiments. J Econ Surv 27(3):491–514
Sheremeta RM, Zhang J (2010) Can groups solve the problem of over-bidding in contests? Soc Choice Welf 35(2):175–197
Spiliopoulos L, Ortmann A, Zhang L (2018) Complexity, attention, and choice in games under time constraints: a process analysis. J Exp Psychol Learn Mem Cogn 44(10):1609
Stahl DO (1993) Evolution of smartn players. Games Econom Behav 5(4):604–617
Stahl DO II, Wilson PW (1994) Experimental evidence on players’ models of other players. J Econ Behav Organ 25(3):309–327
Su L, Shi Z, Phillips PC (2016) Identifying latent structures in panel data. Econometrica 84(6):2215–2264
Sutton J (1998) Technology and market structure—theory and history. MIT Press, New York
Szymanski S (2003) The assessment: the economics of sport. Oxf Rev Econ Policy 19(4):467–477
Tibshirani R (1997) The lasso method for variable selection in the cox model. Stat Med 16(4):385–395
Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25(1):44–56
Tullock G (1980) Efficient rent seeking. Texas A&M University Press, College Station
Vamathevan J, Clark D, Czodrowski P, Dunham I, Ferran E, Lee G, Li B, Madabhushi A, Shah P, Spitzer M et al (2019) Applications of machine learning in drug discovery and development. Nat Rev Drug Discov 18(6):463–477
Wagner DN (2020) Economic patterns in a world with artificial intelligence. Evol Inst Econ Rev 17(1):111–131
Wang W, Phillips PC, Su L (2019) The heterogeneous effects of the minimum wage on employment across states. Econ Lett 174:179–185
Weinblat J (2018) Forecasting European high-growth firms-a random forest approach. J Ind Compet Trade 18(3):253–294
Wiedemann M, Niederreiter J (2021) Uncovering latent clusters in cross-border M&A completion data: the role of institutional and economic factors. Working Paper
Wong CH, Siah KW, Lo AW (2019) Estimation of clinical trial success rates and related parameters. Biostatistics 20(2):273–286
Wooldridge JM (2002) Econometric analysis of cross section and panel data. MIT Press, Cambridge, p 108
Xu Y-Z, Zhang J-L, Hua Y, Wang L-Y (2019) Dynamic credit risk evaluation method for e-commerce sellers based on a hybrid artificial intelligence model. Sustainability 11:19
Yafei X, Mitsche D, Avratchenkov K, Torre D, Chessa M, Persenda A (2018) Modularity-based clustering approaches for economics networks. In: 2018 IEEE 4th international conference on computer and communications (ICCC), pp 2036–2039. IEEE
Zarin DA, Tse T, Williams RJ, Carr S (2016) Trial reporting in clinicaltrials.gov-the final rule. N Engl J Med 375(20):1998–2004
Zhang L, Tan J, Han D, Zhu H (2017a) From machine learning to deep learning: progress in machine intelligence for rational drug discovery. Drug Discov Today 22(11):1680–1685
Zhang K, Yang Z, Başar T (2021) Multi-agent reinforcement learning: a selective overview of theories and algorithms. Handb Reinf Learn Control 20:321–384
Zhang Q, Ye T, Essaidi M, Agarwal S, Liu V, Loo BT (2017b) Predicting startup crowdfunding success through longitudinal social engagement analysis. In: Proceedings of the 2017 ACM on conference on information and knowledge management, pp 1937–1946
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The author declares no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Niederreiter, J. Broadening Economics in the Era of Artificial Intelligence and Experimental Evidence. Ital Econ J 9, 265–294 (2023). https://doi.org/10.1007/s40797-021-00171-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40797-021-00171-2