FØFredrik Ødegaard

Fredrik Ødegaard

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Fredrik Ødegaard has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Setting Optimal Reserve Prices using Fine-Tuned Language Models

    by Joshua Foster, Fredrik Odegaard

    Problem definition. Online auction houses must set reserve prices for highly differentiated products whose unstructured descriptions contain valuable demand information. Existing approaches generally require managers to specify product attributes in advance. We ask whether a language model can instead learn from listing descriptions and historical bids to set item-specific reserve prices before bidding begins. Methodology/results. We fine-tune a pretrained text embedding language model using the structural likelihood of auction bids as its training objective. This directs representation learning toward the valuation distribution that determines the reserve decision. We show that consecutive upper bids identify the tail information needed to set an optimal reserve without observing or modeling the number of potential bidders. A split-sample estimator learns the representation on one half of the data and conducts structural estimation and inference conditional on that representation on the other. We apply the method to approximately 65,800 online used-vehicle auctions. With seller values calibrated to match the sale rate among listings, the model implies a counterfactual net increase of $165.8 million, representing a 14.6% increase above the incumbent reserve policy. Managerial implications. The framework translates a listing description and a seller's value into an item-specific reserve recommendation without constructing a product taxonomy or requiring a bid history for the item being priced. It provides an approach to adapting language models for operational decisions in marketplaces where products are heterogeneous and demand-relevant information is recorded in text.

  • Open Access

    Measuring Sustainable Development Using Nonparametric Network Models

    by Roza Azizi, Mehmet A. Begen, Fredrik Odegaard

    With the increasing scarcity of resources and limited production capacity, efficiency is a top priority and a necessity for sustainable development systems. Resource optimization is essential for human well-being and to address current sustainability challenges. We evaluate how effectively sustainable development systems transform inputs into economic, environmental, and social outputs. We view this evaluation process as a sustainability accounting function that provides a benchmark for how successfully resources can be transformed into desired outcomes with minimal undesirable outputs. The Sustainable Development Goals of the United Nations (SDGs of the UN) provide a global framework for coordinating action towards sustainable consumption and production. We use data-driven approaches to assess system effectiveness. We evaluate resource utilization, waste minimization, and long-term planning. Moreover, our proposed method tracks performance through internal processes, rather than treating sustainable development as a black box. It models the system as a three-process network linked by intermediate products and accounts for both desirable and undesirable outputs, as well as regular and incremental inputs. To further enhance the discriminatory power, we develop a super-efficiency extension that enables a finer-grained ranking among efficient performers. We apply the method to 27 EU countries, compare their performance, and obtain insights on how to improve their strategies and optimize sustainability benefits across environmental, economic, and social dimensions. Our findings provide policymakers and organizations with valuable information and recommendations.

  • Open Access

    When Shared Data Softens Competition: Forward-Looking Metrics and Algorithmic Pricing in Service Markets

    by Chris K. Anderson, Peihong Liu, Fredrik Odegaard

    Motivated by enforcement actions involving revenue-management software and benchmarking platforms, we examine how sharing forward-looking operating metrics (e.g., bookings, occupancy forecasts, utilization) can alter competition in capacity-constrained service markets. We model two firms facing logit demand, fixed capacity, and demand uncertainty where demand states are either high or low. In a no-sharing benchmark, algorithms choose a single price ex ante; under information sharing, firms observe a common demand signal and set state-contingent (high or low demand) prices. We characterize equilibrium pricing across demand/capacity regimes and show that the economic relevance of shared metrics depends on whether capacity constraints bind. When capacity is slack in all demand states, sharing does not affect prices or payoffs. When capacity binds in at least one state, sharing has positive value because it enables firms to replace a one-price hedge with state-contingent pricing as prices move toward the unconstrained benchmark in slack (low-demand) periods and toward a scarcity-clearing level when demand is high and capacity binds. This mechanism increases expected revenue and concentrates potential consumer harm in high-demand, capacity-binding periods. The analysis highlights how the design and governance of shared performance metrics-often produced by internal reporting systems and intermediated by third-party platforms-can shape product-market outcomes and regulatory risk.

  • Open Access

    Probabilistic price promotions without obligations

    by Yongqin Lei, Fredrik Ødegaard


  • Open Access

    Decoding Consumer Preferences Using Attention-Based Language Models

    by Joshua Foster, Fredrik Odegaard

    This paper proposes a new demand estimation method using attention-based language models. An encoder-only language model is trained in a two-stage process to analyze the natural language descriptions of used cars from a large US-based online auction marketplace. The approach enables semi-nonparametrically estimation for the demand primitives of a structural model representing the private valuations and market size for each vehicle listing. In the first stage, the language model is fine-tuned to encode the target auction outcomes using the natural language vehicle descriptions. In the second stage, the trained language model's encodings are projected into the parameter space of the structural model. The model's capability to conduct counterfactual analyses within the trained market space is validated using a subsample of withheld auction data, which includes a set of unique "zero shot" instances.

  • On aggregation of technical and revenue efficiency measures

    by Mehmet A. Begen, Fredrik Ødegaard, Jafar Sadeghi


  • Open Access

    Revenue management in sports, live entertainment and arts

    by Mihai Banciu, Andreas Hinterhuber, Fredrik Ødegaard


  • Refined bounds for the non-Archimedean ϵ in DEA

    by Jafar Sadeghi, Mehmet A. Begen, Fredrik Ødegaard


  • Trilateral escalation in the dollar auction

    by Fredrik Ødegaard, Charles Z. Zheng