Publications

Abstract

Implementing Deep Learning in Estimation of Heterogeneous Taste Parameters in Hierarchical Structural Models

Co-authored with Anastasia Lebedeva (MSBA from Simon Business School)

    This paper introduces NN+S, a novel semi-parametric framework that integrates neural networks with structural models to estimate heterogeneous taste parameters with enhanced accuracy and interpretability, offering significant applications in marketing. By designing a neural network architecture that models both observed and unobserved heterogeneity, as well as intra-individual random taste shocks, NN+S captures complex preference structures while retaining structural interpretability. The NN+S model enables companies to predict consumer responses to counterfactual scenarios, such as new product introductions, personalized pricing, or changes in product attributes.
    Validated through Monte Carlo simulations, NN+S effectively recovers the true taste parameters. Empirical results show that NN+S outperforms linear hierarchical Bayesian models (LHBM) and the model by Farrell et al. (2020) (FLM) on a classical margarine purchase dataset for in-sample predictions, leveraging purchase histories for precise targeting and market segmentation. For out-of-sample predictions, NN+S achieves a slightly higher hit rate than alternative approaches. Scalable via standard neural network tools, NN+S empowers marketers to optimize strategies such as dynamic pricing and product recommendations, providing a flexible and interpretable tool for demand estimation.

In development

Abstract

ConjointNet: Combining Conjoint and Consumer Panel Data Using Neural Networks

Co-authored with:
Mitchell Lovett (Simon Business School, Benjamin Forman Professor of Marketing)
Bhoomija Ranjan (Monash Business School, Senior Lecturer)

    Accurate prediction of consumer preferences for new-to-market attributes is critical for successful product development and marketing strategies. This study examines the effectiveness of a novel approach that integrates conjoint survey data (SP data) with panel data on actual purchases (RP data) to improve the reliability of consumer preference predictions for new-to-market attributes (NTMA). By adopting the NN+S approach, we address the challenges associated with the interplay between RP and SP data, specifically focusing on mitigating the issues related to selecting the optimal tightness between these data types and preventing overfitting through a k-fold cross-validation procedure. We illustrate our methodology by applying it to a unique dataset and comparing its performance with an alternative approach (Ellickson et al., 2019). The proposed method demonstrates a substantial performance boost for both same-sample customers and out-of-sample customers, as well as for new-to-market attributes. The proposed method does not require an expert's opinion for selecting the linked attributes, which is an additional improvement over Ellickson et al., 2019.

Abstract

Manual versus Automated Pricing in Online Pricing Simulation Experiment

Co-authored with:
Jeanine Miklos-Thal (Simon Business School, Fred H. Gowen Professor of Economics & Management)
Catherine Tucker (Sloan School of Management, Distinguished Professor of Management)

    Our study examines the impact of rule-based automation on seller competition in the context of online marketplaces. We conducted an online experiment with real human subjects, where participants acted as sellers in a real-time simulated market. Sellers could manually adjust prices or use automated rules. A key feature of our simulation was that each seller participated in both manual and automated markets simultaneously, which allowed us to cancel out any individual seller's effects. We found a positive correlation between the prevalence of automation and price levels. Our results contribute to ongoing discussions about the potential impact of automated pricing on market dynamics and pricing strategies. In particular, our findings indicate that by choosing to follow simple rule-based automation, sellers gave up their market power to other sellers, allowing them to coordinate their prices to achieve higher price level outcomes. The availability of simple rule-based automation enabled sellers to achieve a pricing outcome of a collusive equilibrium, whereas manual pricing forced sellers to race all the way to the bottom, approaching the Nash equilibrium.

Abstract

Estimation of unobserved product characteristics from online reviews using matrix factorization technique

Solo project

    This paper investigates an application of the matrix factorization (MF) approach for the estimation of unobserved product characteristics from online ratings. We illustrate our approach using online reviews from the beer industry. The results show that estimated unobserved characteristics can be associated with observed characteristics, showing potential usage in cases where observed characteristics are not available. At the same time, estimated unobserved characteristics have several advantages over observed characteristics, including relevance, interpretability, and low dimensionality. In the case of the beer industry, the incorporation of estimated unobserved characteristics improves the substitution patterns of the aggregate demand model. This paper quantifies the errors of the estimates and shows that the bias caused by the selection of reviews is negligible. This technique can also be applied for the estimation of characteristics to improve the substitution pattern estimates in industries such as video games, movies, and books.

Abstract

Microeconomic Foundations of Matrix Factorization for Product Ratings

Solo project

    This study explores the theoretical and practical implications of matrix factorization (MF) in predicting product ratings, with a novel focus on the latent factors derived from MF rather than its predictive accuracy. We demonstrate that these latent factors are closely linked to both observed and unobserved product characteristics. Specifically, under the assumption of linear individual preferences, the latent factors align (in a specific sense) with the principal components of all product characteristics, whether observed or unobserved. Furthermore, these latent factors capture the relative importance of each characteristic in shaping individual preference distributions, suggesting that they may provide more nuanced insights into product positioning than principal components derived from standard PCA. The latent factors also exhibit robustness against certain selection biases. These findings position MF as a powerful tool for estimating unobserved product characteristics in industries such as video games, movies, books, and alcohol, among others.