Higher education institutions face heightened accountability for student success. As such, higher education relies heavily on big data to predict student outcomes. This process is problematic because predictive models are developed on historical data, are deficit based, and are focused on student factors, neglecting institutional factors. The purpose of this quantitative study was to validate a locally developed Learning Skills Inventory (LSI) and to identify learning skill predictors of academic success to develop a strengths-based approach for prediction models of academic performance. The findings showed that the LSI instrument demonstrated inconsistent validity. Although most LSI learning skills were identified factors through factor analyses, only several met criteria for extraction. Regression analysis demonstrated a significant predictive relationship of learning skill factors with GPA but accounted for a small amount of the variance in GPA. These results have student experience and practice and policy implications for higher education. As a skill-based component of GPA, learning skills assessment and development should be considered for integration into prematriculation and first semester outreach, services, and curricula. More research is needed to understand other factors that contribute to GPA. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://bibliotheek.ehb.be:2222/en-US/products/dissertations/individuals.shtml.]