Learning dynamic prices in multiseller electronic retail markets with price sensitive customers, stochastic demands, and inventory replenishments

In this paper, we use reinforcement learning (RL) as a tool to study price dynamics in an electronic retail market consisting of two competing sellers, and price sensitive and lead time sensitive customers. Sellers, offering identical products, compete on price to satisfy stochastically arriving demands (customers), and follow standard inventory control and replenishment policies to manage their inventories. In such a generalized setting, RL techniques have not previously been applied. We consider two representative cases: 1) no information case, were none of the sellers has any information about customer queue levels, inventory levels, or prices at the competitors; and 2) partial information case, where every seller has information about the customer queue levels and inventory levels of the competitors. Sellers employ automated pricing agents, or pricebots, which use RL-based pricing algorithms to reset the prices at random intervals based on factors such as number of back orders, inventory levels, and replenishment lead times, with the objective of maximizing discounted cumulative profit. In the no information case, we show that a seller who uses Q-learning outperforms a seller who uses derivative following (DF). In the partial information case, we model the problem as a Markovian game and use actor-critic based RL to learn dynamic prices. We believe our approach to solving these problems is a new and promising way of setting dynamic prices in multiseller environments with stochastic demands, price sensitive customers, and inventory replenishments.

278. Studies on ass's milk: Composition

The total solids of samples of ass's milk ranged from 7·80 to 9·10, the solids-not-fat from 7·14 to 8·50, and the fat from 0·54 to 0·71%. The nitrogen distribution in ass's milk is: casein 39·5, albumin 35·0, globulin 2·7 and non-protein nitrogen 22·8% of the total nitrogen. Ass's milk contains: casein 0·70, albumin 0·62 and globulin 0·07%. The total protein content is 1·39%. Ass's milk is therefore characterized by a low casein, a low globulin and a high albumin content. The non-protein nitrogen consists of amino nitrogen 8·1, urea nitrogen 24·3 and uric acid 0·7 mg./100 ml. of milk. The urea content is twice that present in cow's milk. The mean chloride and lactose contents of the milk samples are 0·037 and 6·1% respectively. The average calcium and phosphorus content of ass's milk are 0·081 and 0·059% respectively. Half the calcium is ionic, and half is in colloidal form. The phosphorus distribution is: total acid soluble 84·0, acid soluble organic 38·5, easily hydrolysable ester 27·4, inorganic 46·0, and colloidal inorganic 23·0 % of the total phosphorus. The ratio of CaO: P2O5 is 1:1. 46 % of the total phosphorus is in ester form; this is high when compared with only 12 % in cow's milk; most of the phosphoric ester forms soluble barium salts, which is a distinguishing feature of ass's milk. The total sulphur content is 15·8 mg./100 ml. The fat has a penetrating odour and is coloured orange-yellow. It has an iodine value of about 86, which is much higher than that for human milk fat. The Reichert (9·5) and Kirschner values (5·7) are low. In general, the composition of ass's milk resembles that of human rather than of cow's milk.

Direct detection of Salmonella without pre-enrichment in milk, ice-cream and fruit juice by PCR against hilA gene

A novel PCR based assay was devised to specifically detect contamination of any Salmonella serovar in milk, fruit juice and ice-cream without pre-enrichment. This method utilizes primers against hilA gene which is conserved in all Salmonella serovars and absent from the close relatives of Salmonella. An optimized protocol, in terms time and money, is provided for the reduction of PCR contaminants from milk, ice-cream and juice through the use of routine laboratory chemicals. The simplicity, efficiency (time taken 3-4 h) and sensitivity (to about 5-10 CFU/ml) of this technique confers a unique advantage over other previously used time consuming detection techniques. This technique does not involve pre-enrichment of the samples or extensive sample processing, which was a pre-requisite in most of the other reported studies. Hence, this assay can be ideal for adoption, after further fine tuning, by food quality control for timely detection of Salmonella contamination as well as other food-borne pathogens (with species specific primers) in food especially milk, ice-cream and fruit juice. (C) 2011 Elsevier Ltd. All rights reserved.

Reinforcement learning applications in dynamic pricing of retail markets

In this paper, we investigate the use of reinforcement learning (RL) techniques to the problem of determining dynamic prices in an electronic retail market. As representative models, we consider a single seller market and a two seller market, and formulate the dynamic pricing problem in a setting that easily generalizes to markets with more than two sellers. We first formulate the single seller dynamic pricing problem in the RL framework and solve the problem using the Q-learning algorithm through simulation. Next we model the two seller dynamic pricing problem as a Markovian game and formulate the problem in the RL framework. We solve this problem using actor-critic algorithms through simulation. We believe our approach to solving these problems is a promising way of setting dynamic prices in multi-agent environments. We illustrate the methodology with two illustrative examples of typical retail markets.