• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.111-126
• /
• 2017

Recommender systems based on association rule mining significantly contribute to seller's sales by reducing consumers' time to search for products that they want. Recommendations based on the frequency of transactions such as orders can effectively screen out the products that are statistically marketable among multiple products. A product with a high possibility of sales, however, can be omitted from the recommendation if it records insufficient number of transactions at the beginning of the sale. Products missing from the associated recommendations may lose the chance of exposure to consumers, which leads to a decline in the number of transactions. In turn, diminished transactions may create a vicious circle of lost opportunity to be recommended. Thus, initial sales are likely to remain stagnant for a certain period of time. Products that are susceptible to fashion or seasonality, such as clothing, may be greatly affected. This study was aimed at expanding association rules to include into the list of recommendations those products whose initial trading frequency of transactions is low despite the possibility of high sales. The particular purpose is to predict the strength of the direct connection of two unconnected items through the properties of the paths located between them. An association between two items revealed in transactions can be interpreted as the interaction between them, which can be expressed as a link in a social network whose nodes are items. The first step calculates the centralities of the nodes in the middle of the paths that indirectly connect the two nodes without direct connection. The next step identifies the number of the paths and the shortest among them. These extracts are used as independent variables in the regression analysis to predict future connection strength between the nodes. The strength of the connection between the two nodes of the model, which is defined by the number of nodes between the two nodes, is measured after a certain period of time. The regression analysis results confirm that the number of paths between the two products, the distance of the shortest path, and the number of neighboring items connected to the products are significantly related to their potential strength. This study used actual order transaction data collected for three months from February to April in 2016 from an online commerce company. To reduce the complexity of analytics as the scale of the network grows, the analysis was performed only on miscellaneous goods. Two consecutively purchased items were chosen from each customer's transactions to obtain a pair of antecedent and consequent, which secures a link needed for constituting a social network. The direction of the link was determined in the order in which the goods were purchased. Except for the last ten days of the data collection period, the social network of associated items was built for the extraction of independent variables. The model predicts the number of links to be connected in the next ten days from the explanatory variables. Of the 5,711 previously unconnected links, 611 were newly connected for the last ten days. Through experiments, the proposed model demonstrated excellent predictions. Of the 571 links that the proposed model predicts, 269 were confirmed to have been connected. This is 4.4 times more than the average of 61, which can be found without any prediction model. This study is expected to be useful regarding industries whose new products launch quickly with short life cycles, since their exposure time is critical. Also, it can be used to detect diseases that are rarely found in the early stages of medical treatment because of the low incidence of outbreaks. Since the complexity of the social networking analysis is sensitive to the number of nodes and links that make up the network, this study was conducted in a particular category of miscellaneous goods. Future research should consider that this condition may limit the opportunity to detect unexpected associations between products belonging to different categories of classification.

• Applied Biological Chemistry
• /
• v.21 no.3
• /
• pp.150-184
• /
• 1978

Nutritional characteristics and physio-chemical properties of mycelial growth and fruitbody formation of oyster mushroom(Pleurotus ostreatus)in synthetic media, the curtural condition for the commerical production in the rice straw and poplar sawdust media, and the changes of the chemical components of the media and mushroom during the cultivation were investigated. The results can be summarized as follows: 1. Among the carbon sources mannitol and sucrose gave rapid mycelial growth and rapid formation of fruit-body with higher yield, while lactose and rhamnose gave no mycelial growth. Also, citric acid, succinic acid, ethyl alcohol and glycerol gave poor fruit-body formation, and acetic acid, formic acid, fumaric acid, n-butyl alcohol, n-propyl alcohol and iso-butyl alcohol inhibited mycelial growth. 2. Among the nitrogen sources peptone gave rapid mycelial growth and rapid formation of fruit-body with higher yield, while D,L-alanine, asparatic acid, glycine and serine gave very poor fruit-body formation, and nitrite nitrogens, L-tryptophan and L-tyrosine inhibited mycelial growth. Inorganic nitrogens and amino acids added to peptone were effective for fruit-body growth, and thus addition of ammonium sulfate, ammonium tartarate, D,L-alanine and L-leucine resulted in about 10% increase fruit-body yield. L-asparic acid about 15%, L-arginine about 20%, L-glutamic acid, and L-lysine about 25%. 3. At C/N ratio of 15.23 fruit-body formation was fast, but the yield decreased, and at C/N ratio of 11.42 fruit-body formation was slow, but the yield increased. Also, at the same C/N ratio the higher the concentration of mannitol and petone, the higher yield was produced. Thus, from the view point of both yield of fruit-body and time required for fruiting the optimum C/N ratio would be 30. 46. 4. Thiamine, potassium dihydrogen phosphate and magnecium sulfate at the concentration of $50{\mu}g%$. 0.2% and 0.02-0.03%, respectively, gave excellent mycelial and fruit-body growth. Among the micronutrients ferrous sulfate, zinc sulfate and manganese sulfate showed synergetic growth promoting effect but lack of manganese resulted in a little reduction in mycelial and fruit-body growth. The optimum concentrati on of each these nutrients was 0.02mg%. 5. Cytosine and indole acetic acid at 0.2-1mg% and 0.01mg%, respectively, increased amount of mycelia, but had no effect on yield of fruit-body. The other purine and pyrimidine bases and plant hormones also had no effect on mycelial and fruit-belly yield. 6. Illumination inhibited mycelial growth, but illumination during the latter part of vegetative growth induced primordia formation. The optimum light intensity and exposure time was 100 to 500 lux and 6-12 hours per day, respectively. Higher intensity of light was injurous, and in darkness only vegetative growth without primordia formation was continued. 7. The optimum temperature for mycelial growth was $25^{\circ}C$ and for fruit-body formation 10 to $15^{\circi}C$. The optimum pH range was from 5.0 to 6.5. The most excellent fry it-body formation were produced from the mycelium grown for 7 to 10 days. The lesser the volume of media, the more rapid the formation of fruit-body; and the lower the yield of fruit-body; and the more the volume of media, the slower the formation of fruit-body, and the higher the yield of fruit-body. The primordia formation was inhibited by $CO_2$. 8. The optimum moisture content for mycelial growth was over 70% in the bottle media of rice straw and poplar sawdust. 10% addition of rice bran to the media exhibited excellent mycelial growth and fruit-body formation, and the addition of calciumcarbonate alone was effective, but the addition of calcium carbonate was ineffective in the presence of rice bran. 9. In the cultivation experiments the total yield of mushroom from the rice straw media was $14.99kg/m^2$, and from the sawdust media $6.52kg/m^2$, 90% of which was produced from the first and second cropping period. The total yield from the rice straw media was about 2.3 times as high as that from the sawdust media. 10. Among the chemical components of the media little change was observed in the content of ash on the dry weight basis, and organic matter content decreased as the cultivation progressed. Moisture content, which was about 79% at the time of spawning, decreased a little during the period of mycelial propagation, after which no change was observed. 11. During the period from spawning to the fourth cropping about 16.7% of the dry matter, about 19.3% of organic matter, and about 40% of nitrogen were lost from the rice straw media; about 7.5% of dry mallet, about 7.6% of organic matter, and about 20% of nitrogen were lost from the sawdust media. For the production of 1kg of mushroom about 232g of organic matter and about 7.0g of nitrogen were consumed from the rice straw media; about 235g of organic matter and about 6.8g of nitrogen were consumed from the sawdust media, 1㎏ of mushroom from either of media contains 82.4 and 82.3g of organic matter and 5.6 and 5.4g of nitrogen, respectively. 12. Total nitrogen content of the two media decreased gradually as the cultivation progressed, and total loss of insoluble nitrogen was greater than that of soluble nitrogen. Content of amino nitrogen continued to increase up to the third cropping time, after which it decreased. 13. In the rice straw media 28.0 and 13.8% of the total pentosan and ${\alpha}$-cellulose, respectively, lost during the whole cultivation period was lost during the period of mycelial growth; in the sawdust media 24.1 and 11.9% of the total pentosan and ${\alpha}$-cellulose, respectively, was lost during the period of mycelial growth. Lignin content in the media began to decrease slightly from the second cropping time, while the content of reduced sugar, trehalose and mannitol continued to increase. C/N ratio of the rice straw media decreased from 33.2 at spawining to 30.0 at ending; that of the sawdust media decreased from 61.3 to 60.0. 14. In both media phosphorus, potassium, manganese and zinc decreased, at magnesium, calcium and copper showed irregular changes, and iron had a tendency to be increased. 15. Enzyme activities are much higher in the rice straw media than in the sawdust media. CMC saccharifying and liquefying activity gradually increased from after mycelial propagation to the second cropping, after which it decreased in both media. Xylanase activity rapidly and greatly increased during the second cropping period rather than the first period. At the start of the third cropping period the activity decreased rapidly in the rice straw media, which was not observed in the sawdust media. Protease activity was highest after mycelial propagation, after which it gradually decreased. The pH of the rice straw media decreased from 6.3 at spawning to 5.0 after fourth cropping; that of the sawdust media decreased from 5.7 to 4.9. 16. The contents of all the components except crude fibre of the mushroom from the rice straw media were higher than those from the sawdust media. Little change was observed in the content of the components of mushroom cropped from the first to the third period, but slight decrease was noticed at the fourth cropping.