Browsing by Author "Mamo, Daniel"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Application of Data Mining Technology to Support Fraud Protection: the Case of Ethiopian Revenue and Custom Authority
    (Addis Ababa University, 2013-01) Mamo, Daniel; Teferi, Dereje(PhD)
    Taxes are important sources of public revenue. The existence of collective consumption of goods and services necessitates putting some of our income into government hands. However, collection of tax is the main source of income for the government; it is facing difficulties with fraud. Fraud involves one or more persons who intentionally act secretly to deprive the government income and use for their own benefit. Fraud is as old as humanity itself and can take an unlimited variety of different forms. Fraudulent claims account for a significant portion of all claims received by auditors, and cost billions of dollars annually. This study is initiated with the aim of exploring the potential applicability of the data mining technology in developing models that can detect and predict fraud suspicious in tax claims with a particular emphasis to Ethiopian Revenue and Custom Authority. The research has tried to apply first the clustering algorithm followed by classification techniques for developing the predictive model, K-Means clustering algorithm is employed to find the natural grouping of the different tax claims as fraud and non-fraud. The resulting cluster is then used for developing the classification model. The classification task of this study is carried out using the J48 decision tree and Naïve Bayes algorithms in order to create model that best predict fraud suspicious tax claims. To collect the data the researcher used interview and observation for primary data and database analysis for secondary data. The experiments have been conducted following the six-step Cios et al. (2000) KDD process model. For the experiment, the collected tax payers‟ dataset is preprocessed to remove outliers, fill in ITMD values, select relevant attributes, integrate data and derive attributes. The preprocessing phase of this study really took the highest portion of the study time. In this study, different characteristics of the ERCA customers‟ data were collected from the customs ASYCUDA database. A total of 11080 tax payers‟ records are used for training the models, while a separate 2200 records are used for testing the performance of the model. The model developed using the J48 decision tree algorithm has showed highest classification accuracy of 99.98%. This model is then tested with the 2200 testing dataset and scored a prediction accuracy of 97.19%. The results of this study have showed that the data mining techniques are valuable for tax fraud detection. Hence future research directions are pointed out to come up with an applicable system in the area
  • No Thumbnail Available
    Item
    Comparative Study of Leadership Styles of Deans of Government & Private Colleges in Oromia
    (Addis Ababa University, 2007-07) Mamo, Daniel; Shibeshi, Ayalew (Associate Professor)
    This study was conducted to assess the effectiveness oj deans on the selection oj leadership styles. The study was conducted on comparative basis in order to investigate the Jactors that influence leadership style selection by leaders (deans) in the private colleges and their counterparts in the government colleges. An al/empt was made to assess the effectiveness oj deans using Hersey and Blanchard's situational leadership model. The study was conducted in 5 government owned and in 4 privately owned TTC colleges Jound in Oromia Regional state. The samples were deans oj the 9 colleges, administrative and academic employees oj the sample colleges. The sample included 9 deans and 164 administrative and academic employees oj the colleges. /Joth quantitative and qualitative research methods were employed to analyze the data. Statistical analysis using ANOVA and t-test we;s conducted on major ./Clctors that are thought to affect leadership style such as size oj the college as indicated by number oj staffs working in the college, knowledge in the field oj administration oj college deans, work experience and educational qualification oj deans and level oj motivation oj subordinates. The findings showed that size oj the college, work experience, edl/cational ql/alification and knowledge in Ihe field of adminislration oj college deans were not significant Jar Ihe seleclion oj a particular leadership style. However, levels oj motivation oj subordinates seem to affect the selection oj leadership styles oj deans oj' go vernment and private colleges. The majority oj deans oj privately owned colleges exhibit initiating structure leadership style while some (20ut of 5) deans oj government owned colleges exhibit initiating leadership style. Most (301/t 0/5) oj' government owned college deans exhibit transactional leadership style while one dean of privately owned college exhibit il'Onsactional leadership style. It was thus suggested that to improve the leadership CClpacity o.f deans; training Jor incumbent leaders, ejJarts to boost employee morale, training opportunities for both academic and administrative stafJ,' problems such as under representation oj female academe in colleges, appointment of deans in government owned colleges aild Jormulation of college charter must be tackled before deans effectiveness can be realized.
  • No Thumbnail Available
    Item
    Integrated Geophysical Investigation for Chew Bahir Lake Bed Characterization, Southern Ethiopia
    (Addis Ababa Universty, 2014-12) Mamo, Daniel; Haile, Tigistu (PhD)
    This thesis encompasses ground geophysical investigations and examination of previously collected geophysical data at the Chew Bahir, Chelbi Southern Ethiopia. The objectives of the survey was to characterize the Lake bed and proposed core drill sites and check their suitability for obtaining continuous core samples for paleohistory and paleoenvironmental studies. The earlier collected geophysical data include patented seismic data collected by Tullow Oil Plc. The firsthand field data contain electrical resistivity tomography (ERT) and vertical electrical soundings (VES) data over three locations i.e. at the planned core drill site, at an alternative drill site, and at a location adjacent to the valley sides across one of the major alluvial fans. Upon analysis, data from the regional seismic show a dipping bedrock surface away from the valley sides towards the basin center with the suggestion of greater than 5km of unconsolidated sediment at the basin center. The electrical imaging field data map the subsurface to an estimated 70 m below the Lake bed. The results revealed very low apparent resistivity within the basin‟s Lake bed sediments (characteristically less than 1 Ωm), with significantly higher apparent resistivity through the alluvial fan at the valley side (often greater than 500 Ωm). Inside the very low resistivity area, contrary to the expected horizontally stratified subsurface, small lateral resistivity inhomogeneities were exhibited that are possibly associated with lithological changes and changes in desiccation history. The geophysical signature associated with the alluvial fans was clearly distinguished at the valley side, but no signal of similar features was found over the two suggested drill sites. Based on the geophysical survey to date, a location of UTM 261829N and 521120E is recommended for drilling in a sequence of somewhat uniform Lake deposits. Key words: Electrical Resistivity Tomography, Vertical Electrical Sounding, Seismic Refraction, Inverse Model Sections, Chew Bahir