Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

3617231,0841,445 · Jun 202019922001200920182026
48 results for production models

Model learns product vectors from baskets and browsing sessions for better complementary product recommendations.

problem Inferring complementary products from basket and browsing data.
method Proposes BB2vec model that learns product vectors from both baskets and browsing sessions.
result The BB2vec model improves complementary product recommendations and alleviates the cold start problem.

ProductNet curates high-quality product datasets for better product understanding.

problem Lack of high-quality product datasets for product representation learning.
method Curated high-quality product datasets with a multi-modal deep neural network and active learning.
result Master model yields high categorization accuracy (94.7% top-1 accuracy for 1240 classes).

Model predicts capital flow and product share dynamics in international trade.

problem Understanding how capital flows between different industrial sectors affects product shares in international trade.
method Stochastic transfer model based on observed scaling relations.
result Model accurately predicts the distribution of product shares and identifies capital condensation.

Paper tackles product categorization with structured and unstructured attributes for large-scale eCommerce.

problem Challenges in categorizing products with thousands of classes and millions of products.
method Compares hierarchical and flat models, uses Deep Learning for feature extraction, combines structured and unstructured attributes.
result Flat models perform better in specific cases, and the proposed approach handles faulty attribute names and values.

New model predicts global oil production and consumption through 2050.

problem Inaccurate past oil production forecasts leading to public interest.
method Analyzes past regional oil production data to predict future production and consumption.
result Predicts global oil production and consumption through 2050, highlighting limited potential for unconventional oil.

Pricing bonus certificates and barrier products uses efficient interpolation and stochastic modeling.

problem Pricing bonus certificates and barrier products with American conditions.
method Efficient interpolation for European conditions, stochastic modeling for American conditions.
result Pricing can be done without stochastic modeling within a certain accuracy range.

Classifies CAD model descriptions and names from product websites.

problem Distinguishing product descriptions from other text and identifying product names.
method Paragraph vectors, character-level LSTM, word embeddings LSTM tagger.
result Promising results for distinguishing product descriptions and names.

A new method for analyzing product competition using low-dimensional embeddings.

problem Computational challenges in studying product-level competition for millions of products.
method Product2Vec, a method based on representation learning algorithm Word2Vec.
result The method produces more accurate demand forecasts and price elasticities compared to state-of-the-art models.

The paper improves consumer preference modeling by considering multiple product categories.

problem Estimating consumer preferences across multiple product categories with varying attributes and price sensitivity.
method Extends matrix factorization techniques to account for time-varying product attributes and out-of-stock products, pooling information across categories to estimate heterogeneity in preferences.
result The model improves over traditional approaches, accurately estimating consumer preferences and price sensitivity.

Few attempts have been proposed in order to describe the statistical features and historical evolution of the export bipartite matrix countries/products. An important standpoint is the introduction of a products network, namely a hierarchical forest of products that models the formation and the evolution of commodities…

2015-08-14abs ↗pdf ↗

Study optimizes product assortment for retailers with repeated exposures and patience costs.

problem Optimizing product assortment for online retailers with repeated exposures and varying consumer patience.
method Developed a cascade multinomial logit model to capture repeated exposures and patience costs.
result Proposed an approximation solution to the assortment optimization problem.

Geometric cohomology model uses co-oriented maps to define a product structure.

problem Constructing a geometric model for cohomology of smooth manifolds.
method Develops a cochain complex model based on co-oriented smooth maps, focusing on their pull-back product structure.
result Geometric cochains with a partially defined product structure induce the cup product in cohomology.

We construct a theoretical model for equilibrium distribution of workers across sectors with different labor productivity, assuming that a sector can accommodate a limited number of workers which depends only on its productivity. A general formula for such distribution of productivity is obtained, using the detail-bala…

2012-05-11abs ↗pdf ↗

Productivity and credit limits affect aggregate production in non-monotonic ways.

problem Understanding how aggregate production is influenced by individual characteristics and financial constraints.
method Analytical proof of non-monotonic effects of productivity and credit limits on aggregate production in a general equilibrium model.
result Equilibrium aggregate production can be non-monotonic in both individual productivity and credit limit.

We consider in a market model the cooperative emergence of value due to a positive feedback between perception of needs and demand. Here we consider also a negative feedback from production of the traded products, and find that this cooperativity is robust, provided that the production rate is slow. Cooperativity is fo…

2003-09-24abs ↗pdf ↗

Deep sum-product networks learn faster than shallow models.

problem The speed of parameter optimization in sum-product networks.
method Theoretical analysis and empirical experiments on overparameterized sum-product networks.
result Gradient-based optimization in deep sum-product networks is equivalent to gradient ascent with adaptive and time-varying learning rates and additional momentum terms.

A model for learning customer preferences in a dynamic product launch setting.

problem Learning customer preferences in a setting with new product launches.
method Proposes a sequential multinomial logit (SMNL) model and a learning algorithm with a regret bound.
result Demonstrates the tier structure can mitigate risks associated with learning new products.

Study information geometry of warped product spaces, finding special connections.

problem Understanding information geometry in warped product spaces.
method Examined warped products with dually flat connections, characterized connections on base space.
result Characterized connections on base space R>0\mathbb{R}_{>0} as αα-connections with α=±1α= \pm{1}.

The paper proposes a machine learning approach for production forecasting without model calibration.

problem Generating accurate production forecasts for reservoir development.
method Sequential model aggregation using machine learning algorithms without model calibration.
result The proposed method provides robust multi-step-ahead production forecasts.

Warped product construction for Finsler manifolds with curvature conditions.

problem Constructing new Finslerian manifolds with specific curvature properties.
method Extending the warped product concept to Finsler metrics, particularly (α,β)(α,β)-metrics.
result Demonstrated the feasibility of constructing new Finslerian manifolds with prescribed curvature conditions.

A new neural network model ONCF improves collaborative filtering by explicitly modeling embedding correlations.

problem Improving collaborative filtering for better recommendation quality.
method ONCF uses an outer product to model embedding correlations and a convolutional layer to learn high-order correlations.
result ONCF outperforms existing models in implicit feedback data experiments.

Study identifies Markov chain model parameters from small assortments.

problem Identifying parameters of Markov chain choice models from large assortments.
method Simple and efficient algorithm to recover parameters from assortments of sizes two and three.
result Parameters of the Markov chain choice model can be identified from assortments of sizes two and three.

We derive relations between theoretical properties of restricted Boltzmann machines (RBMs), popular machine learning models which form the building blocks of deep learning models, and several natural notions from discrete mathematics and convex geometry. We give implications and equivalences relating RBM-representable …

2012-06-02abs ↗pdf ↗

A simpler measure of economic complexity derived from product diversity.

problem Economic growth theory's reliance on GDP as the sole indicator of a country's capabilities.
method Log Product Diversity (LPD) derived from a combinatorial model of production.
result LPD better predicts economic growth than conventional variables like GDP and human capital.

A model shows faster energy transition rewards flexible production more quickly.

problem Energy transition discourages investments in flexible production.
method Modeling future electricity prices from residual load, investigating revenues for various flexibility levels.
result Faster energy transition rewards flexible production more quickly.

Model predicts future electricity production and flows in Europe.

problem Anticipate changes in electricity production and flows due to energy transition.
method Constructed aggregated pan-European model coupled with dispatch algorithm.
result Large power fluctuations can be absorbed via increased electricity exchanges.

A new pricing strategy maximizes revenue in high-dimensional product spaces with varying customer preferences.

problem Maximizing revenue in a high-dimensional product space with heterogeneous price sensitivity.
method Proposes M3P, a pricing policy that achieves a specific regret bound under heterogeneous price sensitivity.
result Achieves a TT-period regret of O(log(Td)(T+dlog(T)))O(\log(Td) (\sqrt{T} + d\log(T))).

Study improves product categorization on Amazon using multi-modal fusion.

problem Multi-label product categorization in e-commerce.
method Late fusion of image, description, and title modalities using modified CNN and ResNet-50 models.
result Tri-modal late fusion model achieved an F1F_1 score of 88.2%, significantly better than single modal models.

Sum-Product-Quotient Networks boost generative model power by incorporating conditional distributions.

problem Limited expressivity of Sum-Product Networks (SPNs).
method Integrates conditional distributions using quotient nodes and provides tractability conditions.
result Proves SPQNs can compute some distributions more efficiently than SPNs, reducing size requirements.

TXtract extracts structured knowledge from thousands of product categories.

problem Extracting structured knowledge from diverse product categories in e-commerce.
method TXtract uses a taxonomy-aware model with category conditional self-attention and multi-task learning.
result TXtract outperforms state-of-the-art approaches by up to 10% in F1 and 15% in coverage across all categories.

Study optimizes dynamic product selection and pricing using censored preference feedback.

problem Maximizing revenue from dynamic assortment and pricing decisions.
method Proposes a censored multinomial logit model and LCB pricing strategy combined with UCB or TS product selection.
result Achieves optimal regret bounds for dynamic pricing and selection.

Labor productivity in developed countries is analyzed and modeled. Modeling is based on our previous finding that the rate of labor force participation is a unique function of GDP per capita. Therefore, labor productivity is fully determined by the rate of economic growth, and thus, is a secondary economic variable. In…

2008-11-13abs ↗pdf ↗

Estimates the dimension of Kronecker product models using Jacobian rank and tropical morphism.

problem Estimating the dimension of Kronecker product models.
method Using Jacobian rank and tropical morphism to describe the limit of the model.
result Combinatorial conditions for the expected dimension and proof for binary restricted Boltzmann machine.

CDLF predicts product life-cycles in cold-start phases with high accuracy.

problem Forecasting new products in early phases when data is scarce.
method Conditional Diffusion Life-cycle Forecaster (CDLF) combining static descriptors, reference trajectories, and new observations.
result CDLF outperforms classical models in accuracy and probabilistic forecasting.