We consider the problem of recommending relevant content to users of an internet platform in the ... more We consider the problem of recommending relevant content to users of an internet platform in the form of lists of items, called slates. We introduce a variational Bayesian Recurrent Neural Net recommender system that acts on time series of interactions between the internet platform and the user, and which scales to real world industrial situations. The recommender system is tested both online on real users, and on an offline dataset collected from a Norwegian web-based marketplace, FINN.no, that is made public for research. This is one of the first publicly available datasets which includes all the slates that are presented to users as well as which items (if any) in the slates were clicked on. Such a data set allows us to move beyond the common assumption that implicitly assumes that users are considering all possible items at each interaction. Instead we build our likelihood using the items that are actually in the slate, and evaluate the strengths and weaknesses of both approache...
The object of the thesis is to investigate, measure and analyse the impact of liquidity on portfo... more The object of the thesis is to investigate, measure and analyse the impact of liquidity on portfolio value, risk and execution. We consider the formalism of [Acerbi and Scandolo, 2008] to value portfolios in markets exposed to illiquidity through the use of Marginal Supply Demand Curves. We show that future portfolio returns become fat-tailed when liquidity risk is introduced. Further, we investigate the market impact model of [Almgren et al., 2005], who estimates supply curves on equity instruments by considering a large database of executed orders. Since such data are highly confidential, we propose to use transaction data to estimate the same supply curves. This may enable more market participants to assess their liquidity risks and costs. Transaction data does not contain the same information as order data. To bridge the information gap between the two data sets, we introduce a ’strategy identifier’. By using regression and filtering techniques we show that using transaction dat...
ACM Reference Format: Simen Eide, Arnoldo Frigessi, Helge Jenssen, David S. Leslie, Joakim Rishau... more ACM Reference Format: Simen Eide, Arnoldo Frigessi, Helge Jenssen, David S. Leslie, Joakim Rishaug, and Sofie Verrewaere. 2021. FINN.no Slates Dataset: A new Sequential Dataset Logging Interactions, all Viewed Items and Click Responses/NoClick for Recommender Systems Research. In Fifteenth ACM Conference on Recommender Systems (RecSys ’21), September 27-October 1, 2021, Amsterdam, Netherlands. ACM, New York, NY, USA, 3 pages. https://doi.org/10.1145/ 3460231.3474607
Recommendation algorithms are widely adopted in marketplaces to help users find the items they ar... more Recommendation algorithms are widely adopted in marketplaces to help users find the items they are looking for. The sparsity of the items by user matrix and the cold-start issue in marketplaces pose challenges for the off-the-shelf matrix factorization based recommender systems. To understand user intent and tailor recommendations to their needs, we use deep learning to explore various heterogeneous data available in marketplaces. This paper summarizes five lessons we learned from experimenting with state-of-the-art deep learning recommenders at the leading Norwegian marketplace FINN.no. We design a hybrid recommender system that takes the user-generated contents of a marketplace (including text, images and meta attributes) and combines them with user behavior data such as page views and messages to provide recommendations for marketplace items. Among various tactics we experimented with, the following five show the best impact: staged training instead of end-to-end training, levera...
We consider the problem of recommending relevant content to users of an internet platform in the ... more We consider the problem of recommending relevant content to users of an internet platform in the form of lists of items, called slates. We introduce a variational Bayesian Recurrent Neural Net recommender system that acts on time series of interactions between the internet platform and the user, and which scales to real world industrial situations. The recommender system is tested both online on real users, and on an offline dataset collected from a Norwegian web-based marketplace, FINN.no, that is made public for research. This is one of the first publicly available datasets which includes all the slates that are presented to users as well as which items (if any) in the slates were clicked on. Such a data set allows us to move beyond the common assumption that implicitly assumes that users are considering all possible items at each interaction. Instead we build our likelihood using the items that are actually in the slate, and evaluate the strengths and weaknesses of both approache...
We consider the problem of recommending relevant content to users of an internet platform in the ... more We consider the problem of recommending relevant content to users of an internet platform in the form of lists of items, called slates. We introduce a variational Bayesian Recurrent Neural Net recommender system that acts on time series of interactions between the internet platform and the user, and which scales to real world industrial situations. The recommender system is tested both online on real users, and on an offline dataset collected from a Norwegian web-based marketplace, FINN.no, that is made public for research. This is one of the first publicly available datasets which includes all the slates that are presented to users as well as which items (if any) in the slates were clicked on. Such a data set allows us to move beyond the common assumption that implicitly assumes that users are considering all possible items at each interaction. Instead we build our likelihood using the items that are actually in the slate, and evaluate the strengths and weaknesses of both approache...
The object of the thesis is to investigate, measure and analyse the impact of liquidity on portfo... more The object of the thesis is to investigate, measure and analyse the impact of liquidity on portfolio value, risk and execution. We consider the formalism of [Acerbi and Scandolo, 2008] to value portfolios in markets exposed to illiquidity through the use of Marginal Supply Demand Curves. We show that future portfolio returns become fat-tailed when liquidity risk is introduced. Further, we investigate the market impact model of [Almgren et al., 2005], who estimates supply curves on equity instruments by considering a large database of executed orders. Since such data are highly confidential, we propose to use transaction data to estimate the same supply curves. This may enable more market participants to assess their liquidity risks and costs. Transaction data does not contain the same information as order data. To bridge the information gap between the two data sets, we introduce a ’strategy identifier’. By using regression and filtering techniques we show that using transaction dat...
ACM Reference Format: Simen Eide, Arnoldo Frigessi, Helge Jenssen, David S. Leslie, Joakim Rishau... more ACM Reference Format: Simen Eide, Arnoldo Frigessi, Helge Jenssen, David S. Leslie, Joakim Rishaug, and Sofie Verrewaere. 2021. FINN.no Slates Dataset: A new Sequential Dataset Logging Interactions, all Viewed Items and Click Responses/NoClick for Recommender Systems Research. In Fifteenth ACM Conference on Recommender Systems (RecSys ’21), September 27-October 1, 2021, Amsterdam, Netherlands. ACM, New York, NY, USA, 3 pages. https://doi.org/10.1145/ 3460231.3474607
Recommendation algorithms are widely adopted in marketplaces to help users find the items they ar... more Recommendation algorithms are widely adopted in marketplaces to help users find the items they are looking for. The sparsity of the items by user matrix and the cold-start issue in marketplaces pose challenges for the off-the-shelf matrix factorization based recommender systems. To understand user intent and tailor recommendations to their needs, we use deep learning to explore various heterogeneous data available in marketplaces. This paper summarizes five lessons we learned from experimenting with state-of-the-art deep learning recommenders at the leading Norwegian marketplace FINN.no. We design a hybrid recommender system that takes the user-generated contents of a marketplace (including text, images and meta attributes) and combines them with user behavior data such as page views and messages to provide recommendations for marketplace items. Among various tactics we experimented with, the following five show the best impact: staged training instead of end-to-end training, levera...
We consider the problem of recommending relevant content to users of an internet platform in the ... more We consider the problem of recommending relevant content to users of an internet platform in the form of lists of items, called slates. We introduce a variational Bayesian Recurrent Neural Net recommender system that acts on time series of interactions between the internet platform and the user, and which scales to real world industrial situations. The recommender system is tested both online on real users, and on an offline dataset collected from a Norwegian web-based marketplace, FINN.no, that is made public for research. This is one of the first publicly available datasets which includes all the slates that are presented to users as well as which items (if any) in the slates were clicked on. Such a data set allows us to move beyond the common assumption that implicitly assumes that users are considering all possible items at each interaction. Instead we build our likelihood using the items that are actually in the slate, and evaluate the strengths and weaknesses of both approache...
Uploads
Papers by Simen Eide