The paper discusses the bias of investors and the affect it has on the volatility of the stocks in the market. We also show how sentiment analysis can be run on the pulled tweets and why we chose the Microsoft Azure sentiment analyzer over the other commercial sentiment analyzer tools. Finally, we provide some future direction where we plan to take this research forward and conclude with some closing remarks.

For people who are not exposed to the financial markets but who would be interested to invest in stocks for them it is important to know which ticker symbols to follow, based on which investment decisions can be made. In this work, we propose how we can classify stock ticker symbols from tweets vertically using P-Trees. The solution described in this paper analyzes 3000 financial and news symbols vertically from the Twitter platform and finds the ticker symbols which are most frequently been discussed. It also provides an ability to scan through the tweet texts associated with the common ticker occurrences so that the context can be identified to help users make better informed business decisions. The paper also discusses on the bias of investors and the affect it has on the volatility of the stocks in the market.

Association rule mining, originally proposed for market basket data, has potential applications in many areas. Spatial data, such as remote sensed imagery (RSI) data, is one of the promising application areas. Extracting interesting patterns and rules from spatial data sets, composed of images and associated ground data, can be of importance in precision agriculture, resource discovery, and other areas. However, in most cases, the sizes of the spatial data sets are too large to be mined in a reasonable amount of time using existing algorithms. In this paper, we propose an efficient approach to derive association rules from spatial data using Peano Count Tree (P-tree) structure. P-tree structure provides a lossless and compressed representation of spatial data. Based on P-trees, an efficient association rule mining algorithm PARM with fast support calculation and significant pruning techniques is introduced to improve the efficiency of the rule mining process. The P-tree based Association Rule Mining (PARM) algorithm is implemented and compared with FP-growth and Apriori algorithms. Experimental results showed that our algorithm is superior for association rule mining on RSI spatial data.

"One person's noise is another person's signal". Outlier detection is used to clean up datasets and also to discover useful anomalies, such as criminal activities in electronic commerce, computer intrusion attacks, terrorist threats, agricultural pest infestations, etc. Thus, outlier detection is critically important in the information-based society. This paper focuses on finding outliers in large datasets using distance-based methods. First, to speedup outlier detections, we revise Knorr and Ng's distance-based outlier definition; second, a vertical data structure, instead of traditional horizontal structures, is adopted to facilitate efficient outlier detection further. We tested our methods against national hockey league dataset and show an order of magnitude of speed improvement compared to the contemporary distance-based outlier detection approaches.

Outlier detection can lead to discovering unexpected and interesting knowledge, which is critical important to some areas such as monitoring of criminal activities in electronic commerce, credit card fraud, etc. In this paper, we developed an efficient density-based outlier detection method for large datasets. Our contributions are: a) we introduce a relative density factor (RDF); b) based on RDF, we propose an RDF-based outlier detection method which can efficiently prune the data points which are deep in clusters, and detect outliers only within the remaining small subset of the data; c) the performance of our method is further improved by means of a vertical data representation, P-trees. We tested our method with NHL and NBA data. Our method shows an order of magnitude speed improvement compared to the contemporary approaches.

Association rule mining (ARM) finds all the association rules in data, that match some measures of interest such as support and confidence. In certain situations where high support is not necessarily of interest, fixed-consequent association-rule mining for confident rules might be favored over traditional ARM. The need for fixed consequent ARM is becoming more evident in a number of applications such as market basket research (MBR) or precision agriculture. Highly confident rules are desired in all situations; however, support thresholds fluctuate with the applications and the data sets under study, as we shall show later. We propose an approach for mining minimal confident rules in the context of fixed-consequent ARM that relieves the user from the burden of specifying a minimum support threshold. We show that the framework suggested herein is efficient and can be easily expanded by adding new pruning conditions pertaining to specific situations.

Outlier detection can lead to discovering unexpected and interesting knowledge, which is critically important to some areas such as monitoring of criminal activities in electronic commerce, credit card fraud, and the like. In This work, we propose an efficient outlier detection method with clusters as by-product, which works efficiently for large datasets. Our contributions are: a) We introduce a local connective factor (LCF); b) Based on LCF, we propose an outlier detection method which can efficiently detect outliers and group data into clusters in a one-time process. Our method does not require the beforehand clustering process, which is the first step in other state-of-the-art clustering-based outlier detection methods; c) The performance of our method is further improved by means of a vertical data representation, P-trees. We tested our method with real dataset. Our method shows around five-time speed improvements compared to the other contemporary clustering-based outlier-detection approaches.

A novel semi-naive Bayesian classifier is introduced that is particularly suitable to data with many attributes. The naive Bayesian classifier is taken as a starting point and correlations are reduced through joining of highly correlated attributes. Our technique differs from related work in its use of kernel-functions that systematically include continuous attributes rather than relying on discretization as a preprocessing step. This retains distance information within the attribute domains and ensures that attributes are joined based on their correlation for the particular values of the test sample. We implement a kernel-based semi-naive Bayesian classifier using P-Trees and demonstrate that it generally outperforms the naive Bayesian classifier as well as a discrete semi-naïve Bayesian classifier.

No abstract available.

Traditional communication networks have functioned only to deliver information packets from one end system to another. As the cost of computing power continues to decrease, it is worthwhile to consider the benefits of adding more of that computing power to the network itself, either to enhance services or to trade off against other costs such as time, bandwidth and storage. This new area of research is called Active Networking. Active networking represents a new approach in which network switches or nodes perform customized computing as the messages flowing through them. This paper proposes a novel approach to atomic commitment of transactions in distributed database systems. In our approach, active nodes participate in the process of atomic commitment of distributed transactions by maintaining passive "blackboards" which record voting status of participant subtransactions. One active node is delegated the coordinator function so that when rendezvous is there, commit decisions can be made. Since the decision is made from an internal network node (selected to be close to the participant nodes), the uncertainty time delay can be significantly reduced. This is especially critical in wide area networks. Other active nodes can be used to suppress duplicated votes sent in the upstream direction. Additionally, once a negative vote is received at any active node, children participants can be notified of the abort decision immediately and therefore much earlier than would otherwise be possible. This approach is shown to yield performance improvements over traditional methods, in terms of delay and network message traffic.

This letter discusses the performance of a link carrying calls of preemptive priorities. General /spl kappa/-dimensional steady-state balance equations are deduced and the computational complexity of two solution methods are compared through an example of three priorities. The performance of the link is studied through two conventional metrics for blocking probabilities and preempting probabilities. The "peaking" phenomenon of the preempting line discussed can be used in the design of switches and networks. The coincidence of the preempting probability line with the blocking probability line, displayed in the discussion of numerical results, suggests that better metrics for preemptive performance must be found.

Because of the trend toward high bandwidth networks, current distributed query processing algorithms need to be modified or redesigned. Existing distributed query processing techniques must be refocused to reduce latency delay, exploit bandwidth-on-demand, handle multicast issues, and reduce the usual transmission and local processing delays. The authors propose a set of strategies designed to help the implementers of distributed query algorithms on high speed, bandwidth-on-demand, wide area networks. A distributed join algorithm using these design strategies is developed. Using an analytical model they show that the time cost for the proposed new distributed join algorithm is only slightly above that of a theoretical lower bound. Thus, they conclude that the algorithm exhibits near optimal performance and should be considered by implementers of distributed database systems on high-speed bandwidth-on-demand networks.

A database concurrency control object called ROLL (request order linked list), which is a linked list of bit vectors, is introduced together with three simple operations available to transactions: POST, CHECK and RELEASE. POST is used to establish serialization order. CHECK is used to determine current resource availability. RELEASE is used to relinquish resources. ROLL is based on the serialization graph testing method, but no system scheduler module is involved. Using ROLL, waiting, restarting, deadlock and livelock are minimized and almost all operations can be invoked in parallel by individual transaction manager modules. The ROLL object, performance, problems and desirable extensions are discussed.>

A fast method is described for performing relational operations and, in particular, for an equijoin between two relations that stand in a one-to-many relationship. The method is based on a bit-vector technique called domain vector acceleration (DVA). The approach to join acceleration is described and compared analytically with two other join accelerators, hybrid-hash join and join indices. Results show that using domain vectors for simple, binary equijoins between very large tables significantly improves the efficiency of the equijoin operation. Domain vectors also reduce the amount of data that must be cached on disk, relative to join indices and materialized views. DVA can be applied to a wide variety of relational operations, including select, interest, union, semijoin and outer join.>

In this paper we show how global serializability and atomic commit can be attained in a Heterogeneous Distributed Database Management System in which each local DBMS is assumed to be an off-the-shelf, binarylicensed commercial product providing the IBM SAA Common Programming Interface ([SAA88]).

The authors consider the problem of optimizing join query processing in a database distributed over a bus type local area network which uses the carrier sense multiple access/collision detection (CSMA/CD) access protocol. Some new algorithms are proposed which use a compatible access protocol, movable slot time division multiplexing (MSTDM), to achieve improved performance over existing algorithms. Analysis of example cases shows the improved performance potential for MSTDM. It is concluded that the proposed algorithms explicitly account for packetization and other costs unaccounted for in existing algorithms. If the overhead of CSMA/CD and MSTDM algorithms is comparable, MSTDM's performance characteristics translate directly into improved distributed join processing.>

Distributed query-processing algorithms for broadcast local-area networks are described which provide execution strategies and estimates of response time. Four semijoin-specific techniques, five transmission-specific techniques, and three size estimation update functions are incorporated into a baseline algorithm. These variants of the baseline algorithm are simulated and their response times compared using randomly generated data. The technique found to be most beneficial, on the average, for general queries involving multiple joining attributes is the composite semijoining technique. When used in combination with composite semijoining, relation transmission and bit-matrix transmission further reduce response time. Bit-matrix transmission is a data compression technique in which single attributes and a bit matrix of the value pairings are sent in place of a composite attribute. The authors examine these techniques in detail and compare their expected response times.>

The order of queries within a transaction and the order of access to granules within a query may sometimes be varied without changing the results of the transaction. The authors have improved performance by accessing granules in inverse order of their frequency of use. They call this inverse hotness ordering, or IHO. They have proposed several methods of estimation and storage of hotness information, and have simulated IHO in a variety of circumstances.>

The efficient processing of distributed database queries is of great importance in a distributed database management system. The algorithm-S described in this research is very efficient and low in complexity. The algorithm assumes uniformly distributed data within the attributes of a relation and data independence across attributes. Natural data reductions which occur in nonjoining attributes with iow data multiplicity are recognized. The method can give far more efficient solutions than methods which ignore these reductions. The processing strategies generated exhibit low response time as well as low total transmission time regardless of the cost objective employed.