Dhruv Sharma

Bio: Dhruv Sharma is an academic researcher from École Normale Supérieure. The author has contributed to research in topics: Random forest & Logistic regression. The author has an hindex of 5, co-authored 33 publications receiving 78 citations.

V-, U-, L- or W-shaped economic recovery after Covid-19: Insights from an Agent Based Model.

Abstract: We discuss the impact of a Covid-19-like shock on a simple model economy, described by the previously developed Mark-0 Agent-Based Model. We consider a mixed supply and demand shock, and show that depending on the shock parameters (amplitude and duration), our model economy can display V-shaped, U-shaped or W-shaped recoveries, and even an L-shaped output curve with permanent output loss. This is due to the economy getting trapped in a self-sustained "bad" state. We then discuss two policies that attempt to moderate the impact of the shock: giving easy credit to firms, and the so-called helicopter money, i.e. injecting new money into the households savings. We find that both policies are effective if strong enough. We highlight the potential danger of terminating these policies too early, although inflation is substantially increased by lax access to credit. Finally, we consider the impact of a second lockdown. While we only discuss a limited number of scenarios, our model is flexible and versatile enough to accommodate a wide variety of situations, thus serving as a useful exploratory tool for a qualitative, scenario-based understanding of post-Covid recovery. The corresponding code is available on-line.

Improving the Art, Craft and Science of Economic Credit Risk Scorecards Using Random Forests: Why Credit Scorers and Economists Should Use Random Forests

Abstract: This paper outlines an approach to improving credit score modeling using random forests and compares random forests with logistic regression. It is shown that on data sets where variables have multicollinearity and complex interrelationships random forests provide a more scientific approach to analyzing variable importance and achieving optimal predictive accuracy. In addition it is shown that random forests should be used in econometric and credit risk models as they provide a powerful too to assess meaning of variables not available in standard regression models and thus allow for more robust findings.

V –, U –, L – Or W–Shaped Economic Recovery After COVID-19: Insights From an Agent Based Model

Abstract: We discuss the impact of a COVID-19--like shock on a simple model economy, described by the previously developed Mark-0 Agent-Based Model. We consider a mixed supply and demand shock, and show that depending on the shock parameters (amplitude and duration), our model economy can display V-shaped, U-shaped or W-shaped recoveries, and even an L-shaped output curve with permanent output loss. This is due to the economy getting trapped in a self-sustained "bad" state. We then discuss two policies that attempt to moderate the impact of the shock: giving easy credit to firms, and the so-called helicopter money, i.e. injecting new money into the households savings. We find that both policies are effective if strong enough. We highlight the potential danger of terminating these policies too early, although inflation is substantially increased by lax access to credit. Finally, we consider the impact of a second lockdown. While we only discuss a limited number of scenarios, our model is flexible and versatile enough to accommodate a wide variety of situations, thus serving as a useful exploratory tool for a qualitative, scenario-based understanding of post-COVID recovery. The corresponding code is available on-line.

Self-planting: digging holes in rough landscapes

Abstract: Motivated by a potential application in economics, we investigate a simple dynamical scheme to produce planted solutions in optimization problems with continuous variables. We consider the perceptron model as a prototypical model. Starting from random input patterns and perceptron weights, we find a locally optimal assignment of weights by gradient descent; we then remove misclassified patterns (if any), and replace them by new, randomly extracted patterns. This "remove and replace" procedure is iterated until perfect classification is achieved. We call this procedure "self-planting" because the "planted" state is not pre-assigned but results from a co-evolution of weights and patterns. We find an algorithmic phase transition separating a region in which self-planting is efficiently achieved from a region in which it takes exponential time in the system size. We conjecture that this transition might exist in a broad class of similar problems.

I*: Optimizing Logistic Regression to Match Ensemble Performance Using Random Forest Variable Importance

Abstract: An automated directed search procedure called interaction miner or I* is outlined as an entity which allows logistic regression models to be built automatically based on theory suggested by random forest variable importance measures of predictive value of attributes. The fact that interaction effects can be added to regression models using intelligent directed information show that predictive models can be built without art and with science. It is unclear how important this is, but it appears ensemble methods derive their power by extracting information about interaction effects in data. Once this is accounted for regression models can match or outperform random forests. Tuning regression to outperform ensemble methods is the goal of this algorithm. It is shown to work on 3 credit data sets. This is an automated heuristic approach based on the observations in various credit and behavioral data sets that out of the box random forest outperforms logistic regression but after tuning based on random forest variable importance logistic regression can be tuned to match or outperform random forest models by adding interaction terms.

Cleaning large correlation matrices: tools from random matrix theory

Abstract: This review covers recent results concerning the estimation of large covariance matrices using tools from Random Matrix Theory (RMT). We introduce several RMT methods and analytical techniques, such as the Replica formalism and Free Probability, with an emphasis on the Marchenko-Pastur equation that provides information on the resolvent of multiplicatively corrupted noisy matrices. Special care is devoted to the statistics of the eigenvectors of the empirical correlation matrix, which turn out to be crucial for many applications. We show in particular how these results can be used to build consistent "Rotationally Invariant" estimators (RIE) for large correlation matrices when there is no prior on the structure of the underlying process. The last part of this review is dedicated to some real-world applications within financial markets as a case in point. We establish empirically the efficacy of the RIE framework, which is found to be superior in this case to all previously proposed methods. The case of additively (rather than multiplicatively) corrupted noisy matrices is also dealt with in a special Appendix. Several open problems and interesting technical developments are discussed throughout the paper.

A New Interpretation of Information Rate

Abstract: If the input symbols to a communication channel represent the outcomes of a chance event on which bets are available at odds consistent with their probabilities (i.e., “fair” odds), a gambler can use the knowledge given him by the received symbols to cause his money to grow exponentially. The maximum exponential rate of growth of the gambler's capital is equal to the rate of transmission of information over the channel. This result is generalized to include the case of arbitrary odds.Thus we find a situation in which the transmission rate is significant even though no coding is contemplated. Previously this quantity was given significance only by a theorem of Shannon's which asserted that, with suitable encoding, binary digits could be transmitted over the channel at this rate with an arbitrarily small probability of error.

Large Unbalanced Credit Scoring Using Lasso-Logistic Regression Ensemble

Abstract: Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data.

Feedback and organizations: Feedback is good, feedback-friendly culture is better.

Abstract: Scholars have noted that an incomplete understanding of various important aspects of feedback still remains prominent (Whitaker & Levy, 2012). The value of organisational feedback culture on feedback outcomes is a recognised gap in the literature. The present article begins with a brief conceptualisation and definition of individual feedback and highlights the element of meaning as a principle intricate to all feedback techniques. The article then builds a case for the added benefits of creating a feedback-friendly culture in order to gain more insight and enhance the meaningfulness of feedback. Three recommendations are offered to support such a culture including the promotion of the learning continuum, the fostering of a trusting climate, and the endorsement of authentic dialogue. Finally, the implications and future research directions are discussed.Keywords: feedback, feedback-friendly culture, psychological safety and trustIn a recent article that has toured the Web globally, Sullivan (2013) describes how Google is using an algorithm-based approach in decision making, incipiently referred to as "people analytics," in order to make room for innovation and growth within the firm. Google's strategic shift toward a people focus has contributed to enhancing the company as a whole. When considering the latest progress of the company based on the evidence shown by the stock market (Giles, 2013), its decision to make this shift paid off. The underlying principle of this novel human resource management strategy is simple: Every important decision that has an impact on future outcomes of the organisation are made by people-it is in the firm's best interest then, to make sure that the management practices of those people are at their finest (Bryant, 2011; Sullivan, 2013). As the research on this company's own internal data has recognised countless times, the number one key characteristic of great leaders as identified by employees is their ability to give frequent, transparent feedback. Proactive feedback practices were unexpectedly rated by associates as more important and influential than leadership experience and technical knowledge (Sullivan, 2013).Individual feedback has generated a fare amount of research and has been developing over several decades (Ashford, Blatt, & VandeWall, 2003). Only recently have researchers and leaders began to think about feedback from a large-scale perspective (Dahling & O'Malley, 2011). The present article provides a brief section on individual feedback and subsequently introduces recent empirical evidence neighbouring the impact of a feedback-friendly culture on organisations. The article then offers guidelines to work toward building and nurturing a feedback-friendly organisational culture based on sound research and experience stemming from more than 20 years of practice in various organisations worldwide. Finally, the article will close with future directions and reflections for researchers and practitioners.FeedbackIndividual feedback has long been utilized as a tool for facilitating improvement and advancement within organisations and businesses (Levy & Williams, 2004). Feedback is defined as a dynamic communication process occurring between two individuals that convey information regarding the receiver's performance in the accomplishment of work-related tasks. For most, feedback is used to provide information on proximal goals and immediate and recent behaviours. It is also utilized to inform members of desirable development and outcomes (Baker, 2010; London, 2003). Evidence shows that a company that makes effective use of feedback practices have a greater competitive advantage especially in today's fierce economic climate (Baker, 2010; Chatman & Cha, 2003). Indeed, feedback is an essential element in organisations because it binds organisational goals with continuity and fluidity, boosts creativity, propels trust, and drives motivation in individuals (Mulder, 2013). …