Learning to Rank an Assortment of Products

We consider the product-ranking challenge that online retailers face when their customers typically behave as “window shoppers.” They form an impression of the assortment after browsing products ranked in the initial positions and then decide whether to continue browsing. We design online learning algorithms for product ranking that maximize the number of customers who engage with the site. Customers’ product preferences and attention spans are correlated and unknown to the retailer; furthermore, the retailer cannot exploit similarities across products, owing to the fact that the products are not necessarily characterized by a set of attributes. We develop a class of online learning-then-earning algorithms that prescribe a ranking to offer each customer, learning from preceding customers’ clickstream data to offer better rankings to subsequent customers. Our algorithms balance product popularity with diversity, the notion of appealing to a large variety of heterogeneous customers. We prove that our learning algorithms converge to a ranking that matches the best-known approximation factors for the offline, complete information setting. Finally, we partner with Wayfair — a multibillion-dollar home goods online retailer — to estimate the impact of our algorithms in practice via simulations using actual clickstream data, and we find that our algorithms yield a significant increase (5–30%) in the number of customers that engage with the site. This paper was accepted by J. George Shanthikumar for the Management Science Special Issue on Data-Driven Prescriptive Analytics.

SISTEM PREDIKSI FUZZY TIME SERIES DAN PERANGKINGAN WEIGHTED PRODUCT PADA PENJUALAN ES BUAH

<p><em>At every start a new business, especially the sale of fruit ice must always pay attention to profit and loss to ensure the continuity of the business, because the true purpose of entrepreneurship is to seek profit. One of the things that can be done is to predict sales profits appropriately so that the seller can determine what to do in the future. Another factor that is also very important is the ranking of the most desirable fruits, because knowing the seller's favorite fruit ranking can determine the stock of fruit which can also affect sales profits. The research, entitled Fuzzy Time Series Prediction System and Weighted Product Ranking in Fruit Ice Sales, is designed to create a system that can predict sales profits every week. This system can also rank customers' favorite fruits in order to determine the stock of the favorite and non-favorite fruit. The results of the calculation of the error value on the prediction of profits obtained the lowest value of 0.21% and for ranking obtained the lowest error value of 0.40% which means the lower the error value obtained, the higher the prediction accuracy.</em></p><p><em><strong>Keywords</strong></em><em>: </em><em>Forecast, Fuzzy, Ranking, Weighted Product</em></p><p><em>Di setiap memulai usaha baru terutama penjualan es buah harus selalu memperhatikan laba maupun rugi untuk menjamin kelangsungan usahanya, karena sejatinya tujuan berwirausaha adalah mencari keuntungan. Salah satu hal yang bisa dilakukan yaitu dengan cara memprediksi keuntungan penjualan secara tepat agar penjual dapat menentukan apa yang harus dilakukan kedepannya. Faktor lain yang juga sangat penting yaitu peringkat buah yang paling diminati, karena dengan mengetahui rangking buah favorit penjual bisa menentukan stok buah yang juga dapat mempengaruhi keuntungan penjualan. Penelitian dengan judul Sistem Prediksi Fuzzy Time Series Dan Perangkingan Weighted Product Pada Penjualan Es Buah ini, dirancang untuk membuat sistem yang dapat memprediksi keuntungan penjualan tiap minggunya. Sistem ini juga dapat merangking buah favorit pelanggan agar dapat menentukan stok buah yang menjadi favorit maupun yang bukan favorit. Hasil perhitungan nilai error pada prediksi keuntungan diperoleh nilai terendah yaitu 0,21% dan untuk perangkingan diperoleh nilai error terendah sebesar 0,40% yang berarti semakin rendah nilai error yang diperoleh maka semakin tinggi akurasi prediksinya.</em></p><p><em><strong>Kata kunci</strong></em><em>: </em><em>Prediksi, Fuzzy, Perangkingan, Weighted Product</em></p>

Sentiment-Enhanced Content-Based System for Online Recommendations and Rating Prediction

The scarcity of dependable product descriptions and limited emotion unmasking capabilities of user-ratings compromise the accuracy of content-based filtering (CBF) systems. This work puts forward a sentiment-enhanced content-based recommender system (SEC-Rec). The model has four modules, namely key feature extraction module, feature sentiment analysis module, recommendation module, and rating prediction module. Key feature extraction module uses hybrid of RAKE and TextRank to uncover key product features. The authors propose a hybridized model HSVADER (Hybrid SVM and VADER) for feature sentiment evaluation. The recommendation module combines sentiment and similarity for robust product ranking strategy. The practical benefits of SEC-Rec are demonstrated using Amazon Camera dataset, and the results are compared to the state of the art. The rating prediction module uses key feature sentiment score to estimate the overall user-rating resolving the multi-criteria decision-making issue. The RMSE value obtained ascertains the effectiveness of the approach compared to recent models.