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.

Profitable Customer Management: A Study in Retail Banking

The increasing focus of relationship marketing and customer relationship management (CRM) studies on issues of customer profitability has led to the emergence of an area of research on profitable customer management. Nevertheless, there is a notable lack of empirical research examining the current practices of firms specifically with regard to the profitable management of customer relationships according to the approaches suggested in theory. This thesis fills this research gap by exploring profitable customer management in the retail banking sector. Several topics are covered, including marketing metrics and accountability; challenges in the implementation of profitable customer management approaches in practice; analytic versus heuristic (‘rule of thumb’) decision making; and the modification of costly customer behavior in order to increase customer profitability, customer lifetime value (CLV), and customer equity, i.e. the financial value of the customer base. The thesis critically reviews the concept of customer equity and proposes a Customer Equity Scorecard, providing a starting point for a constructive dialog between marketing and finance concerning the development of appropriate metrics to measure marketing outcomes. Since customer management and measurement issues go hand in hand, profitable customer management is contingent on both marketing management skills and financial measurement skills. A clear gap between marketing theory and practice regarding profitable customer management is also identified. The findings show that key customer management aspects that have been proposed within the literature on profitable customer management for many years, are not being actively applied by the banks included in the research. Instead, several areas of customer management decision making are found to be influenced by heuristics. This dilemma for marketing accountability is addressed by emphasizing that CLV and customer equity, which are aggregate metrics, only provide certain indications regarding the relative value of customers and the approximate value of the customer base (or groups of customers), respectively. The value created by marketing manifests itself in the effect of marketing actions on customer perceptions, behavior, and ultimately the components of CLV, namely revenues, costs, risk, and retention, as well as additional components of customer equity, such as customer acquisition. The thesis also points out that although costs are a crucial component of CLV, they have largely been neglected in prior CRM research. Cost-cutting has often been viewed negatively in customer-focused marketing literature on service quality and customer profitability, but the case studies in this thesis demonstrate that reduced costs do not necessarily have to lead to lower service quality, customer retention, and customer-related revenues. Consequently, this thesis provides an expanded foundation upon which marketers can stake their claim for accountability. By focusing on the range of drivers and all of the components of CLV and customer equity, marketing has the potential to provide specific evidence concerning how various activities have affected the drivers and components of CLV within different groups of customers, and the implications for customer equity on a customer base level.

Vision based indoor positioning in a retail environment

Modern smart phones often come with a significant amount of computational power and an integrated digital camera making them an ideal platform for intelligents assistants. This work is restricted to retail environments, where users could be provided with for example navigational in- structions to desired products or information about special offers within their close proximity. This kind of applications usually require information about the user's current location in the domain environment, which in our case corresponds to a retail store. We propose a vision based positioning approach that recognizes products the user's mobile phone's camera is currently pointing at. The products are related to locations within the store, which enables us to locate the user by pointing the mobile phone's camera to a group of products. The first step of our method is to extract meaningful features from digital images. We use the Scale- Invariant Feature Transform SIFT algorithm, which extracts features that are highly distinctive in the sense that they can be correctly matched against a large database of features from many images. We collect a comprehensive set of images from all meaningful locations within our domain and extract the SIFT features from each of these images. As the SIFT features are of high dimensionality and thus comparing individual features is infeasible, we apply the Bags of Keypoints method which creates a generic representation, visual category, from all features extracted from images taken from a specific location. A category for an unseen image can be deduced by extracting the corresponding SIFT features and by choosing the category that best fits the extracted features. We have applied the proposed method within a Finnish supermarket. We consider grocery shelves as categories which is a sufficient level of accuracy to help users navigate or to provide useful information about nearby products. We achieve a 40% accuracy which is quite low for commercial applications while significantly outperforming the random guess baseline. Our results suggest that the accuracy of the classification could be increased with a deeper analysis on the domain and by combining existing positioning methods with ours.

Dietary aspects of cow's milk allergy in young children

Cow s milk allergy (CMA) affects about 2-6% of infants and young children. Environmental factors during early life are suggested to play a role in the development of allergic diseases. One of these factors is likely to be maternal diet during pregnancy and lactation. The association between maternal diet and development of CMA in offspring is not well known, but diet could contain factors that facilitate development of tolerance. After an established food allergy, another issue is gaining tolerance towards an antigen that causes symptoms. The strictness of the elimination depends on the individual level of tolerance. This study aimed at validating a questionnaire used to inquire about food allergies in children, at researching associations between maternal diet during pregnancy and lactation and subsequent development of cow s milk allergy in the offspring, and at evaluating the degree of adherence to a therapeutic elimination diet of children with CMA and factors associated with the adherence and age of recovery. These research questions were addressed in a prospective birth cohort born between 1997 and 2004 at the Tampere and Oulu University Hospitals. Altogether 6753 children of the Diabetes Prediction and Prevention (DIPP) Nutrition cohort were investigated. Questionnaires regarding allergic diseases are often used in studies without validation. High-quality valid tools are therefore needed. Two validation studies were conducted here: one by comparing parentally reported food allergies with information gathered from patient records of 1122 children, and the other one by comparing parentally reported CMA with information in the reimbursement records of special infant formulae in the registers of the Social Insurance Institution for 6753 children. Both of these studies showed that the questionnaire works well and is a valid tool for measuring food allergies in children. In the first validation study, Cohen s kappa values were within 0.71-0.88 for CMA, 0.74-0.82 for cereal allergy, and 0.66-0.86 for any reported food allergy. In the second validation study, the kappa value was 0.79, sensitivity 0.958, and specificity 0.965 for reported and diagnosed CMA. To investigate the associations between maternal diet during pregnancy and lactation and CMA in offspring, 6288 children were studied. Maternal diet during pregnancy (8th month) and lactation (3rd month) was assessed by a validated, 181-item semi-quantitative food frequency questionnaire (FFQ), and as an endpoint register-based information on diagnosed CMA was obtained from the Social Insurance Institution and complemented with parental reports of CMA in their children. The associations between maternal food consumption and CMA in offspring were analyzed by logistic regression comparing the highest and lowest quarters with two middle quarters of consumption and adjusted for several potential confounding factors. High maternal intake of milk products (OR 0.56, 95% CI 0.37-0.86 p = 0.002) was associated with a lower risk of CMA in offspring. When stratified according to maternal allergic rhinitis or asthma, a protective association of high use of milk products with CMA was seen in children of allergy-free mothers (OR 0.30, 95% CI 0.13 - 0.69, p < 0.001), but not in children of allergic mothers. Moreover, low maternal consumption of fish during pregnancy was associated with a higher risk of CMA in children of mothers with allergic rhinitis or asthma (OR 1.47, 95% CI 0.96 - 2.27 for the lowest quarter, p = 0.043). In children of nonallergic mothers, this association was not seen. Maternal diet during lactation was not associated with CMA in offspring, apart from an inverse association between citrus and kiwi fruit consumption and CMA. These results imply that maternal diet during pregnancy may contain factors protective against CMA in offspring, more so than maternal diet during lactation. These results need to be confirmed in other studies before giving recommendations to the public. To evaluate the degree of adherence to a therapeutic elimination diet in children with diagnosed CMA, food records of 267 children were studied. Subsequent food records were examined to assess the age at reintroduction of milk products to the child s diet. Nine of ten families adhered to the elimination diet of the child with extreme accuracy. Older and monosensitized children had more often small amounts of cow s milk protein in their diet (p < 0.001 for both). Adherence to the diet was not related to any other sociodemographic factor studied or to the age at reintroduction of milk products to the diet. Low intakes of vitamin D, calcium, and riboflavin are of concern in children following a cow s milk-free diet. In summary, we found that the questionnaires used in the DIPP study are valid in investigating CMA in young children; that there are associations between maternal diet during pregnancy and lactation and the development of CMA in offspring; and that the therapeutic elimination diet in children with diagnosed CMA is rigorously adhered to.

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.

Encouraging the implication of shops in the city by means of retail associationism. The case of Bilbao

[EN] Retail activity in urban areas constitutes a key variable in the health of a city. For that reason, the processes of urban revitalization and retail revitalization run in parallel manner. Integrated management models for urban centres constitute a good framework to harness the competitiveness of the cities and their retail businesses, but they require of all implied participation, by means of a public – private cooperation.

Digestibility and nutrient utilization of soybean milk concentrate based diets in Oreochromis niloticus

The digestibility and utilisation of two fresh soybean milk concentrate based diets, two stale soybean milk concentrate based diets and two Fishman based diets serving as control, at optimal (30%) and suboptimal (20%) protein levels were evaluated in Oreochromis niloticus. The diets were as follows: Diet I (control) - fishmeal based diet at 30% crude protein, Diet II (control) Fishman based diet at 20% crude protein, Diet III - fresh soybean milk concentrate based diet at 30% crude protein, Diet IV - fresh soybean milk concentrate based diet at 20%, Diet V - stale soybean milk concentrate based diet at 30% crude protein, Diet VI-stale soybean milk concentrate based diet at 20%. Dry matter digestibility differed not significantly with variation in diets (P:0.05). A significant variation was recorded in the protein, lipid and ash digestibility. Proteins were more digestible at optimum than suboptimum level. Ash digestibility was lowest of all the nutrients. Variations in the utilisation of the diets in terms of weight gain, specific growth rate, food conversion ration, protein efficiency ration and apparent net protein utilization were insignificant (P: 0.05). All diets compared favourably with the standard control diet Diet I. This findings suggest the suitability of stale soybean milk concentrate utilisation as protein supplements in the diets of late fry Oreochromis niloticus

Prevalence of Listeria monocytogenes in Idiazabal cheese

Este trabajo se encuentra bajo la licencia Creative Commons Attribution 3.0.