Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDeep Neural Networks for Choice Analysis: A Statistical Learning Theory Perspective
212
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
While researchers increasingly use deep neural networks (DNN) to analyze individual choices, overfitting and interpretability issues remain as obstacles in theory and practice. By using statistical learning theory, this study presents a framework to examine the tradeoff between estimation and approximation errors, and between prediction and interpretation losses. It operationalizes the DNN interpretability in the choice analysis by formulating the metrics of interpretation loss as the difference between true and estimated choice probability functions. This study also uses the statistical learning theory to upper bound the estimation error of both prediction and interpretation losses in DNN, shedding light on why DNN does not have the overfitting issue. Three scenarios are then simulated to compare DNN to binary logit model (BNL). We found that DNN outperforms BNL in terms of both prediction and interpretation for most of the scenarios, and larger sample size unleashes the predictive power of DNN but not BNL. DNN is also used to analyze the choice of trip purposes and travel modes based on the National Household Travel Survey 2017 (NHTS2017) dataset. These experiments indicate that DNN can be used for choice analysis beyond the current practice of demand forecasting because it has the inherent utility interpretation, the flexibility of accommodating various information formats, and the power of automatically learning utility specification. DNN is both more predictive and interpretable than BNL unless the modelers have complete knowledge about the choice task, and the sample size is small. Overall, statistical learning theory can be a foundation for future studies in the non-asymptotic data regime or using high-dimensional statistical models in choice analysis, and the experiments show the feasibility and effectiveness of DNN for its wide applications to policy and behavioral analysis.
rate research
Read More
While deep neural networks (DNNs) have been increasingly applied to choice analysis showing high predictive power, it is unclear to what extent researchers can interpret economic information from DNNs. This paper demonstrates that DNNs can provide economic information as complete as classical discrete choice models (DCMs). The economic information includes choice predictions, choice probabilities, market shares, substitution patterns of alternatives, social welfare, probability derivatives, elasticities, marginal rates of substitution (MRS), and heterogeneous values of time (VOT). Unlike DCMs, DNNs can automatically learn the utility function and reveal behavioral patterns that are not prespecified by domain experts. However, the economic information obtained from DNNs can be unreliable because of the three challenges associated with the automatic learning capacity: high sensitivity to hyperparameters, model non-identification, and local irregularity. To demonstrate the strength and challenges of DNNs, we estimated the DNNs using a stated preference survey, extracted the full list of economic information from the DNNs, and compared them with those from the DCMs. We found that the economic information either aggregated over trainings or population is more reliable than the disaggregate information of the individual observations or trainings, and that even simple hyperparameter searching can significantly improve the reliability of the economic information extracted from the DNNs. Future studies should investigate other regularizations and DNN architectures, better optimization algorithms, and robust DNN training methods to address DNNs three challenges, to provide more reliable economic information from DNN-based choice models.
We present a hierarchical architecture based on Recurrent Neural Networks (RNNs) for predicting disaggregated inflation components of the Consumer Price Index (CPI). While the majority of existing research is focused mainly on predicting the inflation headline, many economic and financial entities are more interested in its partial disaggregated components. To this end, we developed the novel Hierarchical Recurrent Neural Network (HRNN) model that utilizes information from higher levels in the CPI hierarchy to improve predictions at the more volatile lower levels. Our evaluations, based on a large data-set from the US CPI-U index, indicate that the HRNN model significantly outperforms a vast array of well-known inflation prediction baselines.
Bitcoin as well as other cryptocurrencies are all plagued by the impact from bifurcation. Since the marginal cost of bifurcation is theoretically zero, it causes the coin holders to doubt on the existence of the coins intrinsic value. This paper suggests a normative dual-value theory to assess the fundamental value of Bitcoin. We draw on the experience from the art market, where similar replication problems are prevalent. The idea is to decompose the total value of a cryptocurrency into two parts: one is its art value and the other is its use value. The tradeoff between these two values is also analyzed, which enlightens our proposal of an image coin for Bitcoin so as to elevate its use value without sacrificing its art value. To show the general validity of the dual-value theory, we also apply it to evaluate the prospects of four major cryptocurrencies. We find this framework is helpful for both the investors and the exchanges to examine a new coins value when it first appears in the market.
The long-lasting socio-economic impact of the global financial crisis has questioned the adequacy of traditional tools in explaining periods of financial distress, as well as the adequacy of the existing policy response. In particular, the effect of complex interconnections among financial institutions on financial stability has been widely recognized. A recent debate focused on the effects of unconventional policies aimed at achieving both price and financial stability. In particular, Quantitative Easing (QE, i.e., the large-scale asset purchase programme conducted by a central bank upon the creation of new money) has been recently implemented by the European Central Bank (ECB). In this context, two questions deserve more attention in the literature. First, to what extent, by injecting liquidity, the QE may alter the bank-firm lending level and stimulate the real economy. Second, to what extent the QE may also alter the pattern of intra-financial exposures among financial actors (including banks, investment funds, insurance corporations, and pension funds) and what are the implications in terms of financial stability. Here, we address these two questions by developing a methodology to map the macro-network of financial exposures among institutional sectors across financial instruments (e.g., equity, bonds, and loans) and we illustrate our approach on recently available data (i.e., data on loans and private and public securities purchased within the QE). We then test the effect of the implementation of ECBs QE on the time evolution of the financial linkages in the macro-network of the euro area, as well as the effect on macroeconomic variables, such as output and prices.
The rigorous evaluation of anti-poverty programs is key to the fight against global poverty. Traditional evaluation approaches rely heavily on repeated in-person field surveys to measure changes in economic well-being and thus program effects. However, this is known to be costly, time-consuming, and often logistically challenging. Here we provide the first evidence that we can conduct such program evaluations based solely on high-resolution satellite imagery and deep learning methods. Our application estimates changes in household welfare in the context of a recent anti-poverty program in rural Kenya. The approach we use is based on a large literature documenting a reliable relationship between housing quality and household wealth. We infer changes in household wealth based on satellite-derived changes in housing quality and obtain consistent results with the traditional field-survey based approach. Our approach can be used to obtain inexpensive and timely insights on program effectiveness in international development programs.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
