Cilj pričujoče raziskave je bil ugotoviti ali lahko izboljsamo modele strojnega ucenja za napovedovanje verjetnosti klika skozi napredne vlozitve znacilk. Evalvirali smo pet razlicnih pristopov za ...vlozitve znacilk (vlozitve s skaliranjem, FM vlozitve, vlozitve s kodiranjem, NN vlozitve ter vlozitve z utezevanjem) v kombinaciji s tremi modeli strojnega ucenja (logisticna regresija, faktorizacijske metode in globoke faktorizacijske metode). Vsi razviti pristopi so modularni in jih lahko treniramo loceno ter pripojimo poljubnim modelov v nasem napovednem cevovodu. Skozi medsebojne primerjave smo temeljito evalvirali vse prej omenjene modele ter modele nadgrajene z dodanimi moduli za vlozitve znacilk. Nasi rezultati so pokazali, da lahko s pomocjo modulov za vlozitve znacilk signifikantno izboljsamo napovedne rezultate modelov, ne da bi drasticno povecali cas ucenja.
Industrija video iger je v zadnjem desetletju doZivela izredno hiter razvoj. Vsako leto je izdanih na tisoce video iger, ki jih igrajo milijoni igralcev. Steam je vodilna igralna platforma in ...socialno omrezje, ki uporabnikom omogoca nakup in shranjevanje video iger. Podatki platforme Steam nam omogocajo vpogled v igralne navade njenih uporabnikov in popularnosti iger na platformi. V príspevku raziščemo razmerje med razlicnimi lastnostmi iger na platformi Steam in njihovo popularnostjo. Naloge se lotimo preko implementacije razlicšnih Bayesovskih napovednih modelov, s katerimi skusšamo razumeti kako pri dani igri njena cena, velikost, sštevilo jezikov, zanr in druge lastnosti vplivajo na koncno število igralcev. Najbolj uspešne napovedi dosežemo z zanrskim hierarhicnim modelom.
We tackle the challenge of feature embedding for the purposes of improving the click-through rate prediction process. We select three models: logistic regression, factorization machines and deep ...factorization machines, as our baselines and propose five different feature embedding modules: embedding scaling, FM embedding, embedding encoding, NN embedding and the embedding reweighting module. The embedding modules act as a way to improve baseline model feature embeddings and are trained alongside the rest of the model parameters in an end-to-end manner. Each module is individually added to a baseline model to obtain a new augmented model. We test the predictive performance of our augmented models on a publicly accessible dataset used for benchmarking click-through rate prediction models. Our results show that several proposed embedding modules provide an important increase in predictive performance without a drastic increase in training time.
The video game industry has seen rapid growth over the last decade. Thousands of video games are released and played by millions of people every year, creating a large community of players. Steam is ...a leading gaming platform and social networking site, which allows its users to purchase and store games. A by-product of Steam is a large database of information about games, players, and gaming behavior. In this paper, we take recent video games released on Steam and aim to discover the relation between game popularity and a game's features that can be acquired through Steam. We approach this task by predicting the popularity of Steam games in the early stages after their release and we use a Bayesian approach to understand the influence of a game's price, size, supported languages, release date, and genres on its player count. We implement several models and discover that a genre-based hierarchical approach achieves the best performance. We further analyze the model and interpret its coefficients, which indicate that games released at the beginning of the month and games of certain genres correlate with game popularity.